INDEX

Explanations

company names and technology-related terms

oai_token-act-pair · gpt-3.5-turbo

references to specific brands and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 understandably

-0.63

 Fallout

-0.58

 arrogance

-0.57

 indeed

-0.57

 hypocrisy

-0.57

 animosity

-0.56

 neocons

-0.56

 Gamergate

-0.55

 urge

-0.55

 praises

-0.55

POSITIVE LOGITS

emale

0.70

eva

0.70

.).

0.69

)).

0.69

adra

0.69

 thereof

0.69

etc

0.68

ocity

0.68

ãĤ©

0.67

etc

0.67

Activations Density 0.743%

company names and technology-related terms

references to specific brands and products

No Comments

No Known Activations