INDEX

Explanations

phrases or words related to definitions or decisions

oai_token-act-pair · gpt-3.5-turbo

definitive statements or declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Dragonbound

-0.79

 Mara

-0.70

sth

-0.68

akeru

-0.67

mares

-0.67

Reviewer

-0.67

ĸļ

-0.66

WHERE

-0.63

 Boll

-0.62

worldly

-0.62

POSITIVE LOGITS

initions

1.33

icient

1.14

icit

1.13

initely

1.10

inite

1.06

ensible

1.04

endant

1.04

endants

1.04

aults

1.03

ence

1.02

Activations Density 0.009%

phrases or words related to definitions or decisions

definitive statements or declarations

No Comments

No Known Activations