INDEX

Explanations

terms related to abusive behavior and individuals involved in such behavior

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to abusive behavior and relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

dain

-0.85

stanbul

-0.83

yi

-0.81

hm

-0.79

zig

-0.78

akeru

-0.77

izen

-0.76

hran

-0.76

haar

-0.75

ijk

-0.74

POSITIVE LOGITS

 abusive

1.15

 abuse

1.05

 abusers

0.98

abuse

0.97

 abused

0.96

 abusing

0.91

 undermin

0.90

 abuser

0.90

 behav

0.88

 abuses

0.83

Activations Density 0.014%

terms related to abusive behavior and individuals involved in such behavior

words and phrases related to abusive behavior and relationships

No Comments

No Known Activations