INDEX

Explanations

mentions of caves

oai_token-act-pair · gpt-3.5-turbo

references to caves

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

•Caves

No Comments

Negative Logits

abeth

-0.78

pring

-0.78

icious

-0.78

ICS

-0.71

imated

-0.70

 ACTIONS

-0.70

orporated

-0.69

 ILCS

-0.68

IFA

-0.66

LM

-0.66

POSITIVE LOGITS

 cave

1.07

 Dwell

0.93

 caves

0.92

 paintings

0.79

 canyon

0.77

 hiber

0.76

 collapses

0.74

 dwellings

0.73

 dwelling

0.71

 walls

0.70

Activations Density 0.011%

mentions of caves

references to caves

No Comments

No Known Activations