INDEX

Explanations

instances of significant numerical values or sequences, particularly in code or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

tyka

-0.55

MessageTagHelper

-0.53

 isInitialized

-0.51

 ब्रेकडाउन

-0.50

routeProvider

-0.49

setVerticalGroup

-0.49

WriteAttribute

-0.49

 dramatique

-0.48

 mapStateToProps

-0.48

wati

-0.48

POSITIVE LOGITS

0.56

0.52

 HasFactory

0.47

Lace

0.47

 Lombok

0.47

nebago

0.46

seende

0.44

 Paglinawan

0.44

 cutout

0.44

 Ventura

0.43

Activations Density 0.060%

instances of significant numerical values or sequences, particularly in code or technical contexts

No Comments

No Known Activations