INDEX

Explanations

terms related to things named after specific people or places

oai_token-act-pair · gpt-3.5-turbo

references to entities or concepts being named after people or significant figures

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

ures

-0.78

enaries

-0.78

ipolar

-0.76

emn

-0.73

ilation

-0.73

doms

-0.72

fork

-0.71

 Submission

-0.70

ior

-0.70

ibr

-0.69

POSITIVE LOGITS

 initials

1.05

 surname

0.90

 resemblance

0.89

 plural

0.83

 slang

0.81

 namesake

0.78

 nickname

0.78

 Sanskrit

0.76

 shorthand

0.76

 acronym

0.75

Activations Density 0.065%

terms related to things named after specific people or places

references to entities or concepts being named after people or significant figures

No Comments

No Known Activations