INDEX

Explanations

words related to uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

the phrase "may have" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anding

-0.73

 Crown

-0.70

ament

-0.59

 reinforcement

-0.59

osi

-0.58

etition

-0.58

 Harlem

-0.58

dding

-0.57

 Tribune

-0.56

osa

-0.56

POSITIVE LOGITS

 been

1.16

 gotten

1.13

gotten

1.08

been

0.99

 gone

0.92

 underestimated

0.88

 slipped

0.87

 fallen

0.85

 fooled

0.85

 stumbled

0.85

Activations Density 0.046%

words related to uncertainty or speculation

the phrase "may have" in various contexts

No Comments

No Known Activations