INDEX

Explanations

words related to specific geographical locations

oai_token-act-pair · gpt-3.5-turbo

prepositions and the word "in"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

assetsadobe

-0.73

 Haram

-0.72

TextColor

-0.67

ĪĴ

-0.66

icans

-0.64

ICAN

-0.63

 appre

-0.60

»Ĵ

-0.59

cffffcc

-0.58

ADRA

-0.58

POSITIVE LOGITS

nder

0.98

heit

0.97

velt

0.93

enthal

0.89

hent

0.86

ung

0.83

erman

0.82

hander

0.82

ster

0.81

ghan

0.79

Activations Density 0.172%

words related to specific geographical locations

prepositions and the word "in"

No Comments

No Known Activations