INDEX

Explanations

names starting with "Wanda"

oai_token-act-pair · gpt-3.5-turbo

references to "Anda" or variations of it within the text

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

Negative Logits

sed

-0.90

icka

-0.75

paio

-0.72

lav

-0.71

 deriv

-0.71

bard

-0.70

alcohol

-0.69

dn

-0.66

cffff

-0.66

alties

-0.66

POSITIVE LOGITS

emonium

1.25

 Devi

0.94

ibo

0.87

 Haram

0.84

isance

0.81

wana

0.79

ignt

0.78

ju

0.77

arov

0.77

esque

0.72

Activations Density 0.012%

names starting with "Wanda"

references to "Anda" or variations of it within the text

No Known Activations