INDEX

Explanations

mentions of the word "Hog."

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "Hog" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Catal

-0.83

cence

-0.69

Ross

-0.69

Marc

-0.69

negie

-0.66

cedes

-0.64

 coord

-0.64

fecture

-0.64

elled

-0.63

 Alexis

-0.63

POSITIVE LOGITS

Hog

3.45

hog

3.42

hog

2.91

 Hollow

1.28

 Banner

1.17

Bee

1.15

 Hound

1.04

bog

1.03

ogs

1.02

Hav

1.02

Activations Density 0.035%

mentions of the word "Hog."

mentions of the term "Hog" or variations thereof

No Comments

No Known Activations