INDEX

Explanations

keywords regarding disclaimers, instructions, or specifications

oai_token-act-pair · gpt-3.5-turbo

phrases indicating purpose or intent

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

externalActionCode

-0.66

 VIDEOS

-0.65

 Pledge

-0.64

 reacts

-0.63

falls

-0.62

 wounds

-0.62

é¾įå¥ĳå£«

-0.61

 enjoys

-0.61

»Ĵ

-0.61

 defenses

-0.60

POSITIVE LOGITS

cluded

0.81

ivated

0.81

bidden

0.81

avering

0.78

aneous

0.77

ivable

0.76

ivating

0.76

lain

0.74

clusive

0.74

cd

0.73

Activations Density 0.155%

keywords regarding disclaimers, instructions, or specifications

phrases indicating purpose or intent

No Comments

No Known Activations