INDEX

Explanations

blocked or forbidden actions or terms

oai_token-act-pair · gpt-3.5-turbo

words related to restriction or blocking actions

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

adra

-0.83

efully

-0.75

matically

-0.71

doi

-0.70

zig

-0.69

adan

-0.68

antage

-0.67

LET

-0.66

pered

-0.65

asin

-0.64

POSITIVE LOGITS

 Procedures

0.94

 Ones

0.88

 Assets

0.87

 Parenthood

0.86

By

0.85

 Releases

0.84

escription

0.83

 Alive

0.83

 Expend

0.83

 Statements

0.82

Activations Density 0.145%

blocked or forbidden actions or terms

words related to restriction or blocking actions

No Comments

No Known Activations