INDEX

Explanations

references to various forms of abuse

oai_token-act-pair · gpt-3.5-turbo

instances of the word "abuse" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

travel

-0.78

cil

-0.75

pard

-0.75

izen

-0.72

printed

-0.70

views

-0.69

eday

-0.69

ailed

-0.66

 adventurer

-0.66

 traveler

-0.66

POSITIVE LOGITS

abuse

0.94

 abusing

0.84

 abuse

0.81

 abused

0.79

 perpetrated

0.79

 Abuse

0.76

 inflicted

0.75

 abusers

0.75

ãĥ«

0.74

 abuses

0.71

Activations Density 0.034%

references to various forms of abuse

instances of the word "abuse" in various contexts

No Comments

No Known Activations