INDEX

Explanations

words related to visualization or appearance

oai_token-act-pair · gpt-3.5-turbo

terms related to vision or visibility

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ication

-0.76

yll

-0.76

icate

-0.74

burse

-0.72

icated

-0.72

itans

-0.70

osponsors

-0.68

@#&

-0.67

ITAL

-0.67

icult

-0.66

POSITIVE LOGITS

ĪĴ

0.84

 advoc

0.76

hift

0.73

lihood

0.69

Ħ¢

0.69

 flare

0.67

 Payton

0.67

nette

0.67

ially

0.66

isters

0.66

Activations Density 0.052%

words related to visualization or appearance

terms related to vision or visibility

No Comments

No Known Activations