INDEX

Explanations

the word "Matrix"

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to matrices and their applications

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

sweet

-0.81

liest

-0.79

lies

-0.76

»Ĵ

-0.73

mph

-0.72

hire

-0.69

FUL

-0.68

WAYS

-0.68

OPLE

-0.67

tin

-0.67

POSITIVE LOGITS

 Reloaded

1.23

eering

0.91

 multiplication

0.88

rices

0.79

hematic

0.73

asonic

0.73

iami

0.70

 Factor

0.70

yz

0.69

 Matrix

0.69

Activations Density 0.019%

the word "Matrix"

terms and phrases related to matrices and their applications

No Comments

No Known Activations