INDEX

Explanations

specific scientific or technical terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

StoryboardSegue

-0.68

wnież

-0.59

 calldata

-0.57

 Beſ

-0.55

rilis

-0.54

 AssemblyTitle

-0.54

 насе

-0.53

 dimana

-0.53

wiſe

-0.53

Efq

-0.52

POSITIVE LOGITS

 كومونز

0.73

 محفوظة

0.62

}{*}{}

0.54

addComponent

0.49

 kaynağından

0.49

 Corintios

0.49

Tall

0.48

 preview

0.48

 tallest

0.47

dsky

0.47

Activations Density 2.405%

specific scientific or technical terminology

No Comments

No Known Activations