INDEX

Explanations

phrases related to pointing out or highlighting something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating visual observations or references to seeing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

theless

-0.71

icum

-0.71

uci

-0.68

uga

-0.66

urses

-0.65

etheless

-0.65

nih

-0.64

uala

-0.63

osi

-0.63

ont

-0.63

POSITIVE LOGITS

 below

1.22

 above

0.99

 here

0.89

 screenshots

0.86

 clearly

0.85

 BELOW

0.85

 HERE

0.85

why

0.83

 screenshot

0.83

 therein

0.81

Activations Density 0.057%

phrases related to pointing out or highlighting something

phrases indicating visual observations or references to seeing something

No Comments

No Known Activations