INDEX

Explanations

mentions of locations or places

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Scots."

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

vernment

-0.76

 slic

-0.75

 suspic

-0.71

 mileage

-0.70

Reviewer

-0.68

 livest

-0.68

 laundry

-0.66

JPM

-0.66

ĪĴ

-0.66

Downloadha

-0.66

POSITIVE LOGITS

hirt

1.24

weet

1.20

leeve

1.12

hower

1.09

arnaev

1.05

heet

1.05

onic

1.03

ember

0.98

ween

0.98

rue

0.97

Activations Density 0.033%

mentions of locations or places

instances of the word "Scots."

No Comments

No Known Activations