INDEX

Explanations

verbs or phrases indicating control or limitation

oai_token-act-pair · gpt-3.5-turbo

terms that indicate limitations or boundaries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FORE

-0.82

ashington

-0.82

git

-0.72

rious

-0.69

orah

-0.69

 Samoa

-0.69

swick

-0.68

story

-0.66

Sham

-0.66

tom

-0.65

POSITIVE LOGITS

ively

0.99

 restricting

0.97

 restricts

0.97

 restrictive

0.91

ricted

0.89

 restrictions

0.88

 restriction

0.84

 restricted

0.84

 prohibited

0.83

 inhib

0.83

Activations Density 0.027%

verbs or phrases indicating control or limitation

terms that indicate limitations or boundaries

No Comments

No Known Activations