INDEX

Explanations

code-related terminology and functions in programming documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

arkiv

-0.59

writeFieldEnd

-0.55

PREC

-0.51

/*

-0.50

sher

-0.50

igshid

-0.49

 encu

-0.48

 Ente

-0.47

esor

-0.47

apimachinery

-0.46

POSITIVE LOGITS

TagMode

1.14

__":

0.71

 AssemblyTitle

0.70

__':

0.70

 parseFrom

0.67

 quæ

0.65

OrBuilder

0.63

arraycopy

0.62

гӀ

0.62

rungsseite

0.61

Activations Density 0.050%

code-related terminology and functions in programming documentation

No Comments

No Known Activations