INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

jsxFileName

-0.56

afficheront

-0.55

enterOuterAlt

-0.55

HomeAsUpEnabled

-0.54

cesz

-0.51

expandindo

-0.51

 Parcelable

-0.51

lectic

-0.50

出版年

-0.50

Географија

-0.50

POSITIVE LOGITS

 dial

0.61

PerformLayout

0.59

concat

0.58

dash

0.57

indexOf

0.57

 CiNii

0.55

 PLWABN

0.54

izeit

0.54

urnum

0.54

 urma

0.53

Activations Density 2.442%

programming-related terms and functions

No Comments

No Known Activations