INDEX

Explanations

code-related structures, particularly focusing on data manipulations and mappings in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 disambiguazione

-0.65

SourceChecksum

-0.64

ViewImports

-0.62

SharedCtor

-0.52

 فريبيس

-0.51

 strerror

-0.51

CppMethod

-0.51

ResumeLayout

-0.50

 ویکی‌آمباردا

-0.50

eachtet

-0.49

POSITIVE LOGITS

 scala

0.75

 scal

0.69

Seq

0.68

implicit

0.68

scala

0.66

 implicit

0.66

 implicitly

0.66

 implic

0.65

Seq

0.64

 Scala

0.64

Activations Density 0.132%

code-related structures, particularly focusing on data manipulations and mappings in programming contexts

No Comments

No Known Activations