INDEX

Explanations

mentions related to different brands and products named "Maker"

oai_token-act-pair · gpt-3.5-turbo

references to "maker" in various contexts

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

ses

-0.66

 Territ

-0.64

inators

-0.63

 Dalai

-0.63

?????-

-0.61

ANA

-0.60

 Shal

-0.59

JOHN

-0.59

 Locked

-0.58

 striped

-0.58

POSITIVE LOGITS

pace

1.11

paces

1.00

cham

0.89

Maker

0.79

sonian

0.75

 extraord

0.74

atis

0.73

jing

0.73

ht

0.72

mind

0.72

Activations Density 0.024%

mentions related to different brands and products named "Maker"

references to "maker" in various contexts

No Comments

No Known Activations