INDEX

Explanations

numerical values separated by commas, potentially indicating ratings or quantities

oai_token-act-pair · gpt-3.5-turbo

numeric identifiers or votes associated with a dataset

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ened

-0.73

atre

-0.71

cohol

-0.71

uscript

-0.71

phone

-0.70

stract

-0.70

 Examiner

-0.68

bear

-0.68

aged

-0.67

fet

-0.67

POSITIVE LOGITS

0.92

wcsstore

0.79

0.77

0.76

uously

0.75

 msec

0.72

mph

0.71

UTF

0.71

lbs

0.70

 pounds

0.68

Activations Density 0.032%

numerical values separated by commas, potentially indicating ratings or quantities

numeric identifiers or votes associated with a dataset

No Comments

No Known Activations