INDEX

Explanations

phrases related to keys, answers, or solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 spad

-0.47

تما

-0.46

sam

-0.42

addLine

-0.41

 formation

-0.40

 formate

-0.40

 ozna

-0.39

thoven

-0.39

Station

-0.39

 station

-0.39

POSITIVE LOGITS

DockStyle

0.95

rungsseite

0.90

MLLoader

0.85

 GenerationType

0.84

bootstrapcdn

0.83

 ujednoznacz

0.82

MessageOf

0.81

AnchorStyles

0.78

 Numerade

0.78

TestingModule

0.76

Activations Density 0.262%

phrases related to keys, answers, or solutions

No Comments

No Known Activations