INDEX

Explanations

references to superlatives or rankings in the world

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize superlatives or significant rankings in a global context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ADRA

-0.77

ĪĴ

-0.75

¬¼

-0.75

okane

-0.71

icer

-0.70

xit

-0.70

regon

-0.69

lav

-0.69

POR

-0.68

hift

-0.68

POSITIVE LOGITS

 besides

0.72

(~

0.71

 according

0.69

 bestowed

0.67

behind

0.66

 standings

0.66

 EVER

0.65

 compared

0.64

 today

0.63

.'

0.62

Activations Density 0.147%

references to superlatives or rankings in the world

phrases that emphasize superlatives or significant rankings in a global context

No Comments

No Known Activations