INDEX

Explanations

phrases related to conflicts or contentious situations

oai_token-act-pair · gpt-3.5-turbo

references to attacks, incidents, or actions involving conflict or violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 occasional

-0.70

 occasionally

-0.70

 unforeseen

-0.70

ģĸ

-0.68

chnology

-0.68

heastern

-0.66

 societies

-0.66

earances

-0.66

 careers

-0.65

 wrinkles

-0.64

POSITIVE LOGITS

 Lavrov

0.91

Ms

0.83

Mr

0.82

Mrs

0.78

 Shal

0.76

Zar

0.76

 Teresa

0.76

Aj

0.75

Jas

0.74

 Sheikh

0.73

Activations Density 0.603%

phrases related to conflicts or contentious situations

references to attacks, incidents, or actions involving conflict or violence

No Comments

No Known Activations