INDEX

Explanations

phrases related to various levels of quantity or quality

oai_token-act-pair · gpt-3.5-turbo

references to varying degrees of intensity or magnitude

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

enegger

-0.78

fect

-0.76

sov

-0.71

ory

-0.69

ories

-0.65

MRI

-0.65

 Cyborg

-0.65

orie

-0.65

ãĥĹ

-0.65

 Rounds

-0.65

POSITIVE LOGITS

 crossings

0.92

 assurance

0.83

lining

0.77

hearted

0.77

headed

0.75

 difference

0.71

etting

0.70

quo

0.69

ysis

0.69

ropri

0.68

Activations Density 0.048%

phrases related to various levels of quantity or quality

references to varying degrees of intensity or magnitude

No Comments

No Known Activations