INDEX

Explanations

terms related to different fields of study and expertise

oai_token-act-pair · gpt-3.5-turbo

terms related to various academic and professional disciplines or fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

inki

-0.63

itialized

-0.63

 Krug

-0.62

ãĥ´

-0.59

cknowled

-0.57

guyen

-0.55

ificant

-0.55

é£

-0.55

uted

-0.54

 Bour

-0.54

POSITIVE LOGITS

anship

0.83

utics

0.83

 practices

0.72

 techniques

0.71

 etiquette

0.69

 therapy

0.68

istry

0.68

 practice

0.68

—

0.65

 endeavors

0.65

Activations Density 0.456%

terms related to different fields of study and expertise

terms related to various academic and professional disciplines or fields

No Comments

No Known Activations