INDEX

Explanations

phrases related to someone or something being taken somewhere

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "taken."

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

Negative Logits

lich

-0.72

ullah

-0.68

eers

-0.66

witz

-0.64

Cong

-0.63

ler

-0.62

nder

-0.62

 embr

-0.60

 Pupp

-0.59

psey

-0.59

POSITIVE LOGITS

 aback

1.11

aways

0.97

OVER

0.89

ãĤ¤ãĥĪ

0.86

 ACTIONS

0.84

ãĥĥãĥĪ

0.84

 Taken

0.82

 Mehran

0.78

ĭ

0.75

arnaev

0.75

Activations Density 0.040%

phrases related to someone or something being taken somewhere

occurrences of the word "taken."

No Known Activations