INDEX

Explanations

phrases related to specific actions or events involving law enforcement or criminal activity

oai_token-act-pair · gpt-3.5-turbo

references to notable events or people

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

 sugg

-0.71

STE

-0.66

ufact

-0.66

 ensured

-0.62

 Dietary

-0.61

 maintains

-0.61

 ascert

-0.60

 ensures

-0.60

 Sched

-0.58

 acquired

-0.58

POSITIVE LOGITS

 unfold

0.92

aily

0.76

icol

0.71

 firsthand

0.71

escape

0.71

 emerge

0.69

querade

0.69

pour

0.68

figure

0.67

Advertisements

0.65

Activations Density 0.505%

phrases related to specific actions or events involving law enforcement or criminal activity

references to notable events or people

No Comments

No Known Activations