INDEX

Explanations

negative signs and code-related references in a programming or scripting context

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

WriteBarrier

-0.88

Datuak

-0.79

AndEndTag

-0.79

VersionUID

-0.74

onViewCreated

-0.70

principalTable

-0.70

AnimationFrame

-0.69

StoreMessageInfo

-0.67

StructEnd

-0.65

InstrumentedTest

-0.63

POSITIVE LOGITS

 ajudá

0.57

 Belf

0.54

ympto

0.53

poptosis

0.51

 Tark

0.51

źć

0.50

 Référence

0.49

ौन

0.48

ngdoc

0.47

词

0.47

Activations Density 0.184%

negative signs and code-related references in a programming or scripting context

No Comments

No Known Activations