INDEX

Explanations

phrases related to legal matters and law enforcement

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

articles and references to arrests or legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

ngth

-0.78

pires

-0.76

ivating

-0.64

icious

-0.64

Loading

-0.63

avid

-0.62

ensions

-0.62

runners

-0.62

AMS

-0.61

umbered

-0.60

POSITIVE LOGITS

 refund

1.06

 pardon

1.01

 permit

0.96

 explanation

0.92

 continu

0.91

 apology

0.90

 lawyer

0.88

 restraining

0.88

 exemption

0.87

 rematch

0.87

Activations Density 0.258%

phrases related to legal matters and law enforcement

articles and references to arrests or legal actions

No Comments

No Known Activations