INDEX

Explanations

words related to authorization or authority

oai_token-act-pair · gpt-3.5-turbo

words related to authorization and permission

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enth

-0.91

fish

-0.76

mania

-0.74

ï¸ı

-0.70

mates

-0.69

gaard

-0.68

EMS

-0.67

bows

-0.66

Unity

-0.65

âĺħ

-0.64

POSITIVE LOGITS

 authorizing

1.02

 authorization

0.86

ittees

0.81

 authorized

0.78

authorized

0.78

 authorize

0.77

ittee

0.76

 appropriations

0.75

 permission

0.74

Reviewer

0.73

Activations Density 0.038%

words related to authorization or authority

words related to authorization and permission

No Comments

No Known Activations