INDEX

Explanations

mentions of the name "Tony", especially in the context of sports

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

occurrences of the name "Tony"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

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

tm

-0.72

words

-0.68

geist

-0.65

stuff

-0.59

 likely

-0.58

rences

-0.57

redd

-0.56

 worrying

-0.54

ebook

-0.53

ãģ¦

-0.52

POSITIVE LOGITS

 Romo

1.06

Sop

0.95

 Robbins

0.89

 Hawk

0.88

 Stark

0.86

 Fernand

0.82

 Perkins

0.80

 Podesta

0.80

 Rodham

0.79

 Blair

0.77

Activations Density 0.010%

mentions of the name "Tony", especially in the context of sports

occurrences of the name "Tony"

No Comments

No Known Activations