INDEX

Explanations

words related to the concept of being wrong or doing something incorrectly

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "wrong" and its variations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ivities

-0.75

istration

-0.70

andals

-0.68

mop

-0.68

mable

-0.68

aments

-0.64

amaz

-0.64

inar

-0.64

asis

-0.62

sburg

-0.60

POSITIVE LOGITS

 Wrong

1.20

Correct

0.82

ected

0.78

wrong

0.76

Wr

0.73

 Isles

0.72

nown

0.71

 unfocusedRange

0.71

backer

0.71

 Misc

0.70

Activations Density 0.005%

words related to the concept of being wrong or doing something incorrectly

occurrences of the word "wrong" and its variations

No Known Activations