INDEX

Explanations

references to academic journals and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jang

-0.48

Carex

-0.44

jercicios

-0.43

Objetivo

-0.39

ichthys

-0.36

 misi

-0.36

 laid

-0.36

 immen

-0.35

 Mene

-0.35

 зара

-0.35

POSITIVE LOGITS

MLLoader

0.91

Vol

0.89

Vol

0.88

 Volume

0.82

 StatelessWidget

0.81

Volume

0.80

 Issue

0.78

volume

0.76

 Roskov

0.75

StoryboardSegue

0.74

Activations Density 0.253%

references to academic journals and publications

No Comments

No Known Activations