INDEX

Explanations

proper nouns, specifically companies or organizations

oai_token-act-pair · gpt-3.5-turbo

the occurrences and variations of the term "Inc," indicating references to incorporated entities or companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ĪĴ

-0.80

 Afghans

-0.66

Ħ¢

-0.58

 slowing

-0.57

 living

-0.56

¥µ

-0.56

 backs

-0.56

XV

-0.56

gered

-0.55

 sneaking

-0.55

POSITIVE LOGITS

identally

1.72

redibly

1.62

orpor

1.61

arcer

1.61

orporated

1.58

idental

1.57

orrect

1.54

idents

1.53

idence

1.51

redible

1.48

Activations Density 0.026%

proper nouns, specifically companies or organizations

the occurrences and variations of the term "Inc," indicating references to incorporated entities or companies

No Comments

No Known Activations