INDEX

Explanations

phrases related to actions taken or being taken on something

oai_token-act-pair · gpt-3.5-turbo

words related to physical contact, handling, or manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 retri

-0.65

minist

-0.59

å¥³

-0.57

 scrimmage

-0.57

upon

-0.57

 Siber

-0.56

ä

-0.56

ADRA

-0.56

Balt

-0.55

 Antar

-0.55

POSITIVE LOGITS

olicy

0.90

terday

0.80

acket

0.80

odcast

0.76

undown

0.74

ules

0.72

berra

0.71

onent

0.71

inion

0.71

rodu

0.71

Activations Density 0.016%

phrases related to actions taken or being taken on something

words related to physical contact, handling, or manipulation

No Comments

No Known Activations