INDEX

Explanations

mentions of the word "Love."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Love."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

insula

-0.85

Â¯

-0.82

ocument

-0.80

aution

-0.77

monary

-0.76

ifts

-0.72

 exting

-0.70

ħĭ

-0.69

iaries

-0.69

ä½ľ

-0.69

POSITIVE LOGITS

joy

1.01

lihood

0.99

tsky

0.87

birds

0.84

hound

0.82

fully

0.81

ful

0.81

bird

0.79

 Love

0.78

 Boat

0.78

Activations Density 0.031%

mentions of the word "Love."

occurrences of the word "Love."

No Comments

No Known Activations