INDEX

Explanations

code-related elements or features in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

$_"

-0.77

tangentMode

-0.69

MemoryWarning

-0.65

sizeCache

-0.65

oredCriteria

-0.64

*++

-0.63

posedge

-0.63

 '*')

-0.62

writeFieldEnd

-0.61

expandindo

-0.60

POSITIVE LOGITS

“

0.60

0.57

‘

0.48

「

0.47

“

0.47

WriteLiteral

0.46

 defaultstate

0.42

 selam

0.40

„

0.40

 AssemblyCompany

0.40

Activations Density 0.361%

code-related elements or features in a programming context

No Comments

No Known Activations