INDEX

Explanations

words related to food and medication

oai_token-act-pair · gpt-3.5-turbo

words related to items that are "ed" or in a specific state or condition

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

Kou

-0.69

 shotguns

-0.63

Ø©

-0.63

Story

-0.62

 advertisers

-0.62

 sight

-0.62

ASP

-0.59

[&

-0.59

Nun

-0.58

ATCH

-0.58

POSITIVE LOGITS

uce

1.25

gew

1.17

ict

1.17

monton

1.15

ifice

1.14

icts

1.09

nesday

1.07

inburgh

1.05

mund

1.01

uction

1.00

Activations Density 0.027%

words related to food and medication

words related to items that are "ed" or in a specific state or condition

No Comments

No Known Activations