INDEX

Explanations

terms related to technology and scientific fields

oai_token-act-pair · gpt-3.5-turbo

terms related to various fields of study

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

 stub

-0.70

ATTLE

-0.69

ership

-0.68

 Niet

-0.66

TAM

-0.63

 juicy

-0.62

âĢ¢âĢ¢âĢ¢âĢ¢

-0.62

yond

-0.61

cooked

-0.60

AUT

-0.60

POSITIVE LOGITS

pace

1.19

ilver

1.14

mith

1.05

uits

1.04

hops

0.96

hots

0.93

henko

0.93

heet

0.92

cale

0.92

hift

0.91

Activations Density 0.027%

terms related to technology and scientific fields

terms related to various fields of study

No Comments

No Known Activations