INDEX

Explanations

references to the term "Apache."

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Apache" 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

loo

-1.01

icles

-0.97

icle

-0.87

acea

-0.86

enegger

-0.79

antle

-0.76

orian

-0.75

onne

-0.74

ionic

-0.74

OHN

-0.73

POSITIVE LOGITS

scribed

0.74

FER

0.73

 bung

0.72

fer

0.70

Ã±

0.70

bles

0.66

cise

0.66

 Orioles

0.65

ptive

0.64

peria

0.63

Activations Density 0.038%

references to the term "Apache."

mentions of the term "Apache" in various contexts

No Comments

No Known Activations