INDEX

Explanations

numerical values or quantities

oai_token-act-pair · gpt-3.5-turbo

quantifiable measurements or statistics related to various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

BuyableInstoreAndOnline

-0.72

DNA

-0.69

izza

-0.60

Ret

-0.59

ruct

-0.58

gage

-0.58

RNA

-0.57

adium

-0.56

Target

-0.56

Kings

-0.56

POSITIVE LOGITS

 accordingly

1.04

etheless

1.00

 consequently

0.94

 consequ

0.89

 thereafter

0.81

 moreover

0.81

 importantly

0.79

 furthermore

0.77

 thence

0.72

theless

0.72

Activations Density 0.572%

numerical values or quantities

quantifiable measurements or statistics related to various subjects

No Comments

No Known Activations