INDEX

Explanations

names of people or organizations usually associated with news photographs

oai_token-act-pair · gpt-3.5-turbo

references to photographic credits or attributions in a text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 accordingly

-0.75

 conver

-0.70

 markup

-0.69

 recons

-0.69

 dividends

-0.69

 scaven

-0.67

 predators

-0.66

 reefs

-0.66

 cues

-0.66

 pronouns

-0.64

POSITIVE LOGITS

Bloomberg

1.03

AFP

0.98

Courtesy

0.94

Flickr

0.93

Reuters

0.90

Getty

0.89

CBC

0.88

Library

0.80

picture

0.79

Pool

0.78

Activations Density 0.044%

names of people or organizations usually associated with news photographs

references to photographic credits or attributions in a text

No Comments

No Known Activations