INDEX

Explanations

instances of the word 'consent'

oai_token-act-pair · gpt-3.5-turbo

references to consent

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Tycoon

-0.83

Lens

-0.68

Closure

-0.65

tin

-0.64

GPU

-0.64

mania

-0.64

thin

-0.62

tera

-0.61

nikov

-0.61

nas

-0.61

POSITIVE LOGITS

 consent

0.97

 decree

0.94

 Consent

0.87

 decre

0.81

ajor

0.79

 authorizing

0.78

ing

0.77

ibility

0.74

vironment

0.74

ible

0.73

Activations Density 0.015%

instances of the word 'consent'

references to consent

No Comments

No Known Activations