INDEX

Explanations

social media platform names and related actions such as 'follow' and 'like'

oai_token-act-pair · gpt-3.5-turbo

social media engagement cues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Gathering

-0.59

ersen

-0.59

Ã¨re

-0.58

ript

-0.58

escription

-0.57

nces

-0.57

eur

-0.55

lihood

-0.54

 Extras

-0.53

arks

-0.52

POSITIVE LOGITS

 UNCLASSIFIED

0.62

 Kavanaugh

0.56

widget

0.55

 weekday

0.55

 Subscribe

0.54

 POLIT

0.54

civil

0.53

Subscribe

0.52

 Eisenhower

0.51

Follow

0.51

Activations Density 0.085%

social media platform names and related actions such as 'follow' and 'like'

social media engagement cues

No Comments

No Known Activations