INDEX

Explanations

occurrences of the word "authorize" or its variations

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of authorization and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Unity

-0.76

Cube

-0.76

ï¸ı

-0.75

mania

-0.73

âĺħ

-0.71

 Blend

-0.69

enth

-0.69

icle

-0.67

gaard

-0.67

 Tycoon

-0.66

POSITIVE LOGITS

 authorizing

1.13

 authorize

0.97

 authorization

0.92

 authorised

0.88

 authorized

0.88

 confir

0.87

authorized

0.84

 nomine

0.83

Reviewer

0.83

adian

0.81

Activations Density 0.016%

occurrences of the word "authorize" or its variations

words related to the concept of authorization and permissions

No Comments

No Known Activations