INDEX

Explanations

terms related to antisocial behavior

oai_token-act-pair · gpt-3.5-turbo

terms related to antisocial behavior and sentiments

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

IRO

-0.85

aldi

-0.80

zza

-0.77

llah

-0.74

tained

-0.74

 Duchess

-0.74

shi

-0.74

ãĥį

-0.73

gling

-0.73

 Bundy

-0.72

POSITIVE LOGITS

ocial

1.11

 antis

1.01

antis

0.82

ographs

0.81

ident

0.79

odic

0.78

rep

0.77

ocks

0.77

cellaneous

0.77

olit

0.77

Activations Density 0.020%

terms related to antisocial behavior

terms related to antisocial behavior and sentiments

No Comments

No Known Activations