INDEX

Explanations

phrases related to infinity or endlessness

oai_token-act-pair · gpt-3.5-turbo

concepts related to boundless quantities or limitless possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

acus

-0.84

bourg

-0.78

mast

-0.76

ector

-0.74

iquette

-0.73

*/(

-0.72

ective

-0.72

avid

-0.72

atche

-0.71

stood

-0.69

POSITIVE LOGITS

 regress

1.09

 possibilities

1.05

 amounts

1.04

 supply

0.89

 iterations

0.85

 replay

0.84

 quantities

0.83

 repetition

0.83

 loops

0.83

 amount

0.82

Activations Density 0.053%

phrases related to infinity or endlessness

concepts related to boundless quantities or limitless possibilities

No Comments

No Known Activations