INDEX

Explanations

pronouns and questions

oai_token-act-pair · gpt-3.5-turbo

sentences expressing opinions or judgments about actions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

NAT

-0.63

Balt

-0.61

 ï¿½

-0.60

imet

-0.58

),"

-0.58

ï¿½

-0.57

Â´

-0.57

)",

-0.56

ogenic

-0.56

ï¿½ï¿½ï¿½ï¿½

-0.56

POSITIVE LOGITS

 goddamn

0.82

 irony

0.75

 godd

0.71

 dunno

0.70

 hilar

0.70

 Stupid

0.69

 sucker

0.63

 sane

0.63

 damned

0.63

 Thing

0.61

Activations Density 1.193%

pronouns and questions

sentences expressing opinions or judgments about actions and events

No Comments

No Known Activations