INDEX

Explanations

references to legal or regulatory violations

oai_token-act-pair · gpt-3.5-turbo

terms related to legal violations and regulatory compliance

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ourn

-0.76

aping

-0.70

 parting

-0.66

ENG

-0.65

uilding

-0.65

coming

-0.64

assemb

-0.64

eng

-0.64

apest

-0.62

ington

-0.62

POSITIVE LOGITS

 norms

1.13

 requirements

0.93

 bounds

0.88

 limits

0.88

 obligations

0.86

 standards

0.84

 sensibilities

0.84

 limitations

0.82

 principles

0.82

 criteria

0.81

Activations Density 0.276%

references to legal or regulatory violations

terms related to legal violations and regulatory compliance

No Comments

No Known Activations