INDEX

Explanations

specific programming constructs or cases within code

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

switch statement cases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 pleaſure

-0.53

 tranſ

-0.48

 juſ

-0.48

 marié

-0.44

 houſe

-0.43

 précédentes

-0.41

+#+

-0.41

 précédents

-0.40

cæ

-0.39

ſelf

-0.38

POSITIVE LOGITS

case

0.88

 Case

0.66

subpackage

0.63

Case

0.62

CASE

0.62

 CASE

0.56

daß

0.56

 Casey

0.55

styleType

0.54

Casey

0.51

Activations Density 0.004%

specific programming constructs or cases within code

switch statement cases

No Comments

No Known Activations