INDEX

Explanations

references to criminal investigations and legal proceedings related to assaults and abuse

oai_token-act-pair · gpt-3.5-turbo

terms related to sexual misconduct and the legal system surrounding it

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

WATCH

-0.76

å§«

-0.73

IENT

-0.71

RECT

-0.71

IRD

-0.71

é¾įåĸļå£«

-0.70

Js

-0.69

vale

-0.69

å°Ĩ

-0.67

RANT

-0.66

POSITIVE LOGITS

dq

0.71

 backlog

0.70

 Cambodia

0.67

 hotline

0.65

amph

0.64

 Faul

0.63

 PTSD

0.61

 allowance

0.61

ascus

0.61

 blacklist

0.60

Activations Density 0.358%

references to criminal investigations and legal proceedings related to assaults and abuse

terms related to sexual misconduct and the legal system surrounding it

No Comments

No Known Activations