INDEX

Explanations

references to specific individuals

oai_token-act-pair · gpt-3.5-turbo

names and proper nouns related to individuals and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

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

aceae

-0.79

tons

-0.71

 guiActiveUnfocused

-0.66

"/>

-0.66

inka

-0.59

 McCann

-0.59

wings

-0.58

 crest

-0.57

unda

-0.57

 Lans

-0.57

POSITIVE LOGITS

 host

0.72

 Founder

0.63

 Editor

0.60

cloneembedreportprint

0.58

Fight

0.58

 Analyst

0.55

 MSNBC

0.55

 Breitbart

0.55

ellectual

0.54

*****

0.54

Activations Density 0.145%

references to specific individuals

names and proper nouns related to individuals and entities

No Comments

No Known Activations