INDEX

Explanations

instances of programming-related terminologies and functionalities

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

user input

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.63

richTextPanel

-0.63

 desmotivaciones

-0.59

MemoryWarning

-0.55

AlterField

-0.54

 OFDb

-0.54

 Winaray

-0.54

MigrationBuilder

-0.53

awtextra

-0.53

 symboles

-0.52

POSITIVE LOGITS

AddField

0.79

 חיצוניים

0.48

glo

0.40

GLI

0.38

keto

0.37

 extra

0.35

ranton

0.35

sup

0.35

bru

0.35

Glo

0.34

Activations Density 0.000%

instances of programming-related terminologies and functionalities

user input

No Comments

No Known Activations