INDEX

Explanations

references to changes or modifications

oai_token-act-pair · gpt-3.5-turbo

references to the concept of change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

amina

-0.76

Bei

-0.69

NK

-0.61

 LIMITED

-0.60

 ducks

-0.59

vern

-0.59

 Saud

-0.59

ographies

-0.58

 Peninsula

-0.57

 DRAGON

-0.57

POSITIVE LOGITS

over

1.08

overs

0.96

 effected

0.92

 wrought

0.89

making

0.87

able

0.83

agents

0.80

itri

0.77

maker

0.77

xual

0.77

Activations Density 0.060%

references to changes or modifications

references to the concept of change

No Comments

No Known Activations