INDEX

Explanations

the word "Loretta" followed by various surnames

oai_token-act-pair · gpt-3.5-turbo

the presence of specific names or terms associated with individuals, particularly in a legal or governmental context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

nown

-0.81

urat

-0.73

reau

-0.71

gart

-0.68

 tempting

-0.68

 reimburse

-0.66

odder

-0.62

axter

-0.62

iago

-0.62

rolet

-0.61

POSITIVE LOGITS

å£«

0.72

scope

0.66

vironment

0.64

åĬ

0.64

ktop

0.64

atural

0.63

 Arabian

0.61

esis

0.61

 Strauss

0.61

iae

0.59

Activations Density 0.173%

the word "Loretta" followed by various surnames

the presence of specific names or terms associated with individuals, particularly in a legal or governmental context

No Comments

No Known Activations