INDEX

Explanations

steps or instructions for adding configurations or elements to different systems or software settings

oai_token-act-pair · gpt-3.5-turbo

commands or instructions related to adding items or features in a technical context

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

fare

-0.82

rior

-0.70

ãĤ¡

-0.68

fall

-0.68

grim

-0.65

geist

-0.64

é¾įå¥ĳå£«

-0.64

baum

-0.64

ĸļ

-0.64

walking

-0.63

POSITIVE LOGITS

endum

1.03

itionally

0.98

ition

0.97

itional

0.96

itions

0.95

resses

0.87

icted

0.86

ictions

0.80

ictive

0.80

icts

0.79

Activations Density 0.045%

steps or instructions for adding configurations or elements to different systems or software settings

commands or instructions related to adding items or features in a technical context

No Comments

No Known Activations