INDEX

Explanations

specific programming syntax or structural elements present in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 aDecoder

-0.76

thenReturn

-0.66

AndEndTag

-0.63

 Meksiku

-0.60

TestingModule

-0.56

InitVars

-0.55

henswürdigkeiten

-0.55

addCriterion

-0.53

ThroughAttribute

-0.53

GIVEREF

-0.53

POSITIVE LOGITS

<%@

0.63

 Berwick

0.58

Gare

0.57

 BoxDecoration

0.56

 domino

0.56

ughter

0.56

 Inscrivez

0.53

 Majefty

0.51

RIK

0.51

styleType

0.51

Activations Density 0.133%

specific programming syntax or structural elements present in code

No Comments

No Known Activations