INDEX

Explanations

references to the character "Lex Luthor."

oai_token-act-pair · gpt-3.5-turbo

references to the character Lex Luthor

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

llah

-0.82

ailable

-0.75

xual

-0.74

Ã±o

-0.73

cffffcc

-0.67

ounty

-0.66

ONEY

-0.66

renheit

-0.65

orld

-0.64

ortality

-0.64

POSITIVE LOGITS

 Luthor

1.34

 Machina

1.03

Lex

1.03

Lex

0.98

icon

0.92

Lug

0.89

iazep

0.86

ophon

0.84

iom

0.83

ical

0.82

Activations Density 0.006%

references to the character "Lex Luthor."

references to the character Lex Luthor

No Comments

No Known Activations