INDEX

Explanations

expressions highlighting interactions or relationships between multiple people

oai_token-act-pair · gpt-3.5-turbo

references to interactions among individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Variety

-0.63

ģ

-0.63

QL

-0.62

cit

-0.61

@#&

-0.59

 turnaround

-0.59

thouse

-0.59

 Lans

-0.58

 Hunt

-0.57

 Winter

-0.57

POSITIVE LOGITS

worldly

1.23

selves

0.92

wise

0.75

 mate

0.67

inant

0.66

ope

0.65

loo

0.65

stretched

0.64

friend

0.64

 mutually

0.63

Activations Density 0.028%

expressions highlighting interactions or relationships between multiple people

references to interactions among individuals

No Comments

No Known Activations