INDEX

Explanations

proper nouns related to fashion and various individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and terms associated with the gaming and entertainment industries

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

ITH

-0.88

BILITIES

-0.78

anguage

-0.76

ãģĦ

-0.74

pta

-0.72

UAL

-0.71

 Flavoring

-0.71

FTWARE

-0.71

inventoryQuantity

-0.71

IZE

-0.70

POSITIVE LOGITS

agne

0.99

urations

0.84

rast

0.83

rous

0.81

Duc

0.79

Dup

0.79

orde

0.79

heny

0.78

rice

0.76

ĵĺ

0.75

Activations Density 0.033%

proper nouns related to fashion and various individuals

proper nouns, particularly names and terms associated with the gaming and entertainment industries

No Comments

No Known Activations