INDEX

Explanations

references to the brand "Che" at varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Che" or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

owship

-0.77

 Archdemon

-0.76

etheless

-0.76

 Optimus

-0.73

çīĪ

-0.69

 Kirin

-0.66

icably

-0.66

MFT

-0.65

 eleph

-0.64

 Afgh

-0.64

POSITIVE LOGITS

apeake

0.99

hou

0.92

ards

0.91

dule

0.84

roll

0.79

ets

0.79

anut

0.78

book

0.78

lator

0.78

gre

0.78

Activations Density 0.008%

references to the brand "Che" at varying levels of activation

mentions of the name "Che" or related terms

No Comments

No Known Activations