INDEX

Explanations

words related to conflict and struggle

oai_token-act-pair · gpt-3.5-turbo

terms related to games and films

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

azeera

-0.85

olulu

-0.78

 Dhabi

-0.74

 Flavoring

-0.72

bourg

-0.69

ascar

-0.68

chel

-0.66

Ĥ¬

-0.66

 ILCS

-0.66

annie

-0.66

POSITIVE LOGITS

 itself

1.04

 revolves

0.76

 succeeded

0.73

 proceeded

0.72

 progresses

0.72

 progressed

0.71

's

0.69

 began

0.69

 transitioned

0.69

 motto

0.68

Activations Density 0.423%

words related to conflict and struggle

terms related to games and films

No Comments

No Known Activations