INDEX

Explanations

mentions of the word "house" with associated actions or descriptions

oai_token-act-pair · gpt-3.5-turbo

references to houses or properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aneously

-0.86

aneous

-0.73

DragonMagazine

-0.67

uyomi

-0.67

ICAL

-0.66

iary

-0.65

nesota

-0.65

psey

-0.65

TING

-0.63

irection

-0.63

POSITIVE LOGITS

wife

1.46

wives

1.41

keeping

1.19

mates

1.09

boat

1.04

warming

1.03

plant

1.03

husband

1.01

mate

1.00

boats

1.00

Activations Density 0.027%

mentions of the word "house" with associated actions or descriptions

references to houses or properties

No Comments

No Known Activations