INDEX

Explanations

acronyms related to technological systems

oai_token-act-pair · gpt-3.5-turbo

terms related to positioning systems and their technologies

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

adm

-0.78

istic

-0.77

adesh

-0.76

 ç¥ŀ

-0.75

ãĥ³ãĤ¸

-0.74

ufact

-0.70

 thirds

-0.68

\\\\\\\\\\\\\\\\

-0.68

ãĥ£

-0.67

icidal

-0.66

POSITIVE LOGITS

weet

1.01

ilon

0.90

heet

0.90

ystem

0.89

erver

0.84

ilver

0.83

ometimes

0.83

chal

0.81

hops

0.81

hew

0.80

Activations Density 0.014%

acronyms related to technological systems

terms related to positioning systems and their technologies

No Comments

No Known Activations