INDEX

Explanations

terms related to the word "Heart"

oai_token-act-pair · gpt-3.5-turbo

the word "Heart" and its variations

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

aution

-0.83

aeda

-0.81

BILITIES

-0.74

 liability

-0.74

etheless

-0.71

inational

-0.69

enance

-0.68

BILITY

-0.65

ascus

-0.63

iries

-0.63

POSITIVE LOGITS

beat

1.16

felt

1.03

lake

1.03

burn

1.02

hardt

0.91

 Hearts

0.90

gow

0.89

warming

0.88

bread

0.88

heart

0.87

Activations Density 0.018%

terms related to the word "Heart"

the word "Heart" and its variations

No Comments

No Known Activations