INDEX

Explanations

key phrases involving criticism or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.68

AndEndTag

-0.67

MLLoader

-0.66

TypedDataSet

-0.56

 estekak

-0.53

Хьажоргаш

-0.52

UniformLocation

-0.52

 noqa

-0.50

 ProtoMessage

-0.49

onomía

-0.49

POSITIVE LOGITS

 correct

2.80

 wrong

2.51

correct

2.43

 correctly

2.40

Correct

2.38

 Correct

2.37

 incorrect

2.18

wrong

2.14

 Wrong

2.09

 CORRECT

2.04

Activations Density 0.631%

key phrases involving criticism or questioning

No Comments

No Known Activations