INDEX

Explanations

actions or behaviors that involve physical interaction or engagement

oai_token-act-pair · gpt-3.5-turbo

actions or behaviors that indicate negative or confrontational situations

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

si

-0.86

eria

-0.77

antha

-0.72

see

-0.72

chev

-0.70

skin

-0.68

word

-0.67

tes

-0.67

nings

-0.66

Ã¨re

-0.66

POSITIVE LOGITS

 oneself

1.15

 yourself

0.94

 accordingly

0.81

redients

0.77

 ourselves

0.76

 noises

0.76

 hearts

0.73

 yourselves

0.73

 engagements

0.72

 idiots

0.71

Activations Density 0.313%

actions or behaviors that involve physical interaction or engagement

actions or behaviors that indicate negative or confrontational situations

No Comments

No Known Activations