INDEX

Explanations

words related to law enforcement accountability

oai_token-act-pair · gpt-3.5-turbo

single letters or short substrings that frequently appear in names or terms

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

 glim

-0.90

ITNESS

-0.86

cause

-0.85

wt

-0.85

TPPStreamerBot

-0.85

Tokens

-0.80

umerable

-0.79

ipeg

-0.77

 teasp

-0.75

ĸļ

-0.75

POSITIVE LOGITS

 Gomez

0.99

 Blanc

0.90

Ã¨re

0.88

 Suarez

0.85

aux

0.85

 Parish

0.82

 Aires

0.82

 Gonzalez

0.82

 Grande

0.81

 Gutierrez

0.79

Activations Density 0.248%

words related to law enforcement accountability

single letters or short substrings that frequently appear in names or terms

No Comments

No Known Activations