INDEX

Explanations

programming-related keywords and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 transfieras

-0.60

 gyhoeddwyd

-0.58

 initComponents

-0.58

marle

-0.53

 OFDb

-0.52

Datuak

-0.52

 كومونز

-0.51

 Тогда

-0.49

ällig

-0.48

ValueStyle

-0.47

POSITIVE LOGITS

XmlAccessorType

0.69

0.62

((

0.61

[(

0.57

 self

0.57

ANTLR

0.56

(([

0.56

nil

0.55

XmlSchema

0.55

Activations Density 0.133%

programming-related keywords and identifiers

No Comments

No Known Activations