INDEX

Explanations

numerical values or quantities

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

EndContext

-0.55

BeforeAll

-0.54

-0.53

;->

-0.52

Šaltiniai

-0.51

EnableWeb

-0.50

formik

-0.50

rungsseite

-0.50

 Formen

-0.49

BeginContext

-0.49

POSITIVE LOGITS

StoryboardSegue

0.61

FTFY

0.55

íncia

0.54

udadera

0.51

 textStatus

0.50

 ListTile

0.50

télé

0.50

 initComponents

0.49

peur

0.49

corrência

0.49

Activations Density 0.545%

numerical values or quantities

No Comments

No Known Activations