INDEX

Explanations

words related to permission or authorization

oai_token-act-pair · gpt-3.5-turbo

instances of the word "permit" and its variations

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

tone

-0.86

tops

-0.79

corn

-0.79

kaya

-0.78

tal

-0.73

akening

-0.72

raped

-0.71

cup

-0.70

sung

-0.69

 Chrom

-0.68

POSITIVE LOGITS

Reviewer

1.01

 permitting

0.93

 compr

0.90

 permitted

0.79

ptin

0.78

 permits

0.77

 permit

0.76

conservancy

0.74

 approvals

0.72

 waivers

0.71

Activations Density 0.021%

words related to permission or authorization

instances of the word "permit" and its variations

No Comments

No Known Activations