INDEX

Explanations

references to organized activities or initiatives

oai_token-act-pair · gpt-3.5-turbo

references to various programs

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

pick

-0.68

picking

-0.67

 dilig

-0.65

ween

-0.64

xious

-0.64

 Grip

-0.64

CLASSIFIED

-0.63

Boss

-0.62

 doom

-0.62

ushima

-0.62

POSITIVE LOGITS

mable

1.76

matic

1.46

matically

1.45

mers

1.02

atically

0.94

atical

0.87

 skelet

0.81

lectic

0.80

atic

0.78

¥µ

0.78

Activations Density 0.028%

references to organized activities or initiatives

references to various programs

No Comments

No Known Activations