INDEX

Explanations

phrases indicating speculation or possibility

oai_token-act-pair · gpt-3.5-turbo

constructions that express possibility or speculation

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

reciation

-0.62

anding

-0.61

ocol

-0.59

osa

-0.59

uity

-0.58

 marqu

-0.57

 territ

-0.57

ueless

-0.56

 proclaiming

-0.55

 disclaimer

-0.54

POSITIVE LOGITS

 been

1.24

been

1.11

 Been

1.02

 gotten

0.96

gotten

0.90

 undergone

0.88

 begun

0.79

 come

0.77

 gone

0.75

 arisen

0.75

Activations Density 0.072%

phrases indicating speculation or possibility

constructions that express possibility or speculation

No Comments

No Known Activations