INDEX

Explanations

news organizations, specific television shows, and medical organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names of shows, organizations, and events

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

untled

-0.64

 Pengu

-0.63

actionDate

-0.62

 Takeru

-0.59

owe

-0.56

rone

-0.55

romeda

-0.55

ylene

-0.54

 confidential

-0.53

 intrig

-0.53

POSITIVE LOGITS

verett

0.61

DVD

0.60

rollers

0.59

 Apostles

0.57

 Ascension

0.57

iT

0.56

©¶æ

0.56

vironments

0.56

ement

0.55

endment

0.55

Activations Density 0.704%

news organizations, specific television shows, and medical organizations

proper nouns and names of shows, organizations, and events

No Comments

No Known Activations