INDEX

Explanations

references to actions or processes happening during the runtime of a program or system

oai_token-act-pair · gpt-3.5-turbo

terms related to runtime environments and lifespan

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hips

-0.91

essee

-0.87

ongyang

-0.83

olulu

-0.83

ramid

-0.79

ideon

-0.78

aido

-0.78

etsk

-0.76

ippi

-0.76

ongs

-0.76

POSITIVE LOGITS

 runtime

1.23

 Runtime

0.93

Exception

0.72

UX

0.69

 pollut

0.67

runtime

0.67

NX

0.66

 upkeep

0.65

 Premiere

0.62

è¯

0.62

Activations Density 0.008%

references to actions or processes happening during the runtime of a program or system

terms related to runtime environments and lifespan

No Comments

No Known Activations