INDEX

Explanations

code-related constructs and Python class attributes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-0.63

tvguidetime

-0.54

 académico

-0.51

̈́

-0.51

αι

-0.49

Materiał

-0.48

 ministère

-0.48

yntaxException

-0.47

évêque

-0.46

 armées

-0.46

POSITIVE LOGITS

tagHelperRunner

0.89

httphttps

0.75

ChildScrollView

0.73

interopRequire

0.65

 surla

0.63

 GetEnumerator

0.62

 unknownFields

0.61

antie

0.60

nloa

0.59

<!--[

0.59

Activations Density 0.032%

code-related constructs and Python class attributes

No Comments

No Known Activations