INDEX

Explanations

technical terms and coding-related constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CWE

-0.56

Климат

-0.56

Clik

-0.55

 resourceCulture

-0.53

 defaultstate

-0.49

 poussière

-0.48

<>());

-0.48

fsp

-0.47

 getRule

-0.47

 Paglinawan

-0.47

POSITIVE LOGITS

 IntPtr

0.69

IBarButtonItem

0.68

migrationBuilder

0.68

 recommandée

0.64

 ActionResult

0.63

TargetException

0.61

withCredentials

0.60

annan

0.60

Exploration

0.60

 Morelos

0.60

Activations Density 0.062%

technical terms and coding-related constructs

No Comments

No Known Activations