INDEX

Explanations

phrases indicating a hypothetical situation or suggestion

oai_token-act-pair · gpt-3.5-turbo

expressions of hypothetical or conditional situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

æ³

-0.73

rylic

-0.65

Reporting

-0.64

isted

-0.63

Cook

-0.63

Sem

-0.63

Writing

-0.62

eyed

-0.62

 Handbook

-0.60

 Practices

-0.60

POSITIVE LOGITS

 surely

1.06

 doubtless

0.98

be

0.98

 inevitably

0.97

 undoubtedly

0.97

 never

0.96

 probably

0.91

 definitely

0.91

 assume

0.90

 likely

0.89

Activations Density 0.154%

phrases indicating a hypothetical situation or suggestion

expressions of hypothetical or conditional situations

No Comments

No Known Activations