INDEX

Explanations

mentions of the word "Love" with varying degrees of activation

oai_token-act-pair · gpt-3.5-turbo

the word "Love" and related uses in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ocument

-0.84

 todd

-0.82

ulhu

-0.79

acco

-0.79

ħĭ

-0.77

 reluct

-0.75

aution

-0.74

monary

-0.73

emonium

-0.71

NRS

-0.69

POSITIVE LOGITS

lihood

1.25

joy

1.10

birds

1.03

bird

0.95

 Actually

0.89

good

0.86

watching

0.83

tsky

0.83

fully

0.83

hound

0.82

Activations Density 0.028%

mentions of the word "Love" with varying degrees of activation

the word "Love" and related uses in various contexts

No Comments

No Known Activations