INDEX

Explanations

words related to actions and events happening to specific individuals or communities

oai_token-act-pair · gpt-3.5-turbo

action-oriented verbs indicating significant events or contributions

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

hov

-0.60

 DRAGON

-0.59

ierre

-0.58

Trade

-0.58

 Sapp

-0.57

oooooooooooooooo

-0.56

adra

-0.56

cipled

-0.55

FUN

-0.55

adier

-0.55

POSITIVE LOGITS

by

0.79

monton

0.73

 subur

0.68

eals

0.67

 pione

0.67

ÃĥÃĤ

0.66

nesday

0.65

BY

0.65

DeliveryDate

0.63

ngth

0.63

Activations Density 0.500%

words related to actions and events happening to specific individuals or communities

action-oriented verbs indicating significant events or contributions

No Comments

No Known Activations