INDEX

Explanations

keywords related to personal names and titles, especially when used in formal contexts

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of people

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

formance

-0.78

inar

-0.77

ials

-0.71

versions

-0.69

oids

-0.68

emort

-0.68

itized

-0.68

ils

-0.66

rogens

-0.66

iren

-0.65

POSITIVE LOGITS

NYU

0.79

 University

0.77

 UCLA

0.77

 McGill

0.76

University

0.75

 Harvard

0.75

 Managing

0.74

 Duke

0.72

 Stanford

0.72

 Nort

0.71

Activations Density 0.888%

keywords related to personal names and titles, especially when used in formal contexts

proper nouns and names of people

No Comments

No Known Activations