INDEX

Explanations

phrases that emphasize understanding and insight into various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

WebVitals

-0.84

 AssemblyCulture

-0.77

 kaynağından

-0.70

TabIndex

-0.69

 industriale

-0.67

rícula

-0.64

utilisons

-0.63

QMetaType

-0.62

wnętr

-0.60

 universale

-0.60

POSITIVE LOGITS

 autorytatywna

0.58

 كومونز

0.55

bah

0.50

wikimedia

0.49

ph

0.45

xtext

0.44

WTA

0.43

luk

0.43

jd

0.43

nh

0.43

Activations Density 0.064%

phrases that emphasize understanding and insight into various topics

No Comments

No Known Activations