INDEX

Explanations

phrases indicating authorship or responsibility in a collaborative context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MessageOf

-0.74

AndEndTag

-0.62

SafeAreaView

-0.56

žius

-0.54

DockStyle

-0.54

zło

-0.53

 Вікі

-0.53

 typelib

-0.52

Obrázky

-0.52

 Baillargeon

-0.51

POSITIVE LOGITS

who

0.81

 فريبيس

0.74

 whom

0.66

providedIn

0.62

uxxxx

0.59

who

0.59

 professional

0.57

adpleegd

0.57

 HasFactory

0.56

DotNetBar

0.55

Activations Density 0.433%

phrases indicating authorship or responsibility in a collaborative context

No Comments

No Known Activations