INDEX

Explanations

instances where permission is required or granted

oai_token-act-pair · gpt-3.5-turbo

mentions of permission

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ulative

-0.71

ulz

-0.69

tal

-0.66

itched

-0.65

 Revel

-0.62

oche

-0.62

utton

-0.62

 Beet

-0.61

 Sadd

-0.61

allion

-0.61

POSITIVE LOGITS

 permission

1.06

Reviewer

0.89

 permissions

0.89

 waivers

0.83

 granted

0.79

uthor

0.77

ibl

0.77

essee

0.75

eous

0.75

 clearance

0.75

Activations Density 0.014%

instances where permission is required or granted

mentions of permission

No Comments

No Known Activations