INDEX

Explanations

references to the University of California, Los Angeles (UCLA)

oai_token-act-pair · gpt-3.5-turbo

mentions of the University of California, Los Angeles (UCLA)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

BOOK

-0.78

driving

-0.73

ravings

-0.70

roman

-0.69

horse

-0.69

 wagon

-0.68

ote

-0.68

driven

-0.66

DonaldTrump

-0.66

odic

-0.66

POSITIVE LOGITS

 UCLA

1.30

 Bruins

1.06

 Rosenberg

0.90

USC

0.89

enthal

0.86

 Kobe

0.84

 Fein

0.77

 Bros

0.77

CLA

0.76

 Munich

0.76

Activations Density 0.009%

references to the University of California, Los Angeles (UCLA)

mentions of the University of California, Los Angeles (UCLA)

No Comments

No Known Activations