INDEX

Explanations

key words related to computer software and technology, specifically focusing on file formats and computer programming terms

oai_token-act-pair · gpt-3.5-turbo

abbreviations or specific codes related to technology and communication

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nature

-0.77

 Accountability

-0.74

å£«

-0.73

EVA

-0.73

 Gamble

-0.69

è¦ļéĨĴ

-0.69

 Chaser

-0.69

Downloadha

-0.66

 Seah

-0.66

ingham

-0.65

POSITIVE LOGITS

umen

1.00

mble

0.95

anium

0.91

gment

0.84

umin

0.81

pex

0.80

cean

0.79

ub

0.78

moil

0.77

imet

0.76

Activations Density 0.195%

key words related to computer software and technology, specifically focusing on file formats and computer programming terms

abbreviations or specific codes related to technology and communication

No Comments

No Known Activations