INDEX

Explanations

programming constructs and function return values

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

Code elements before "result" or similar words

np_acts-logits-general · gemini-2.0-flash

variable assignment of result

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

RegressionTest

-0.65

omitempty

-0.64

 Barbier

-0.58

ViewImports

-0.56

Referències

-0.56

//

-0.56

 utafitiHapana

-0.55

bkz

-0.54

 HttpNotFound

-0.54

höhung

-0.53

POSITIVE LOGITS

 result

2.58

result

2.55

 results

2.47

RESULT

2.28

 Result

2.27

Result

2.25

 RESULT

2.21

results

2.19

 resultado

2.15

 Results

2.10

Activations Density 0.072%

programming constructs and function return values

Code elements before "result" or similar words

variable assignment of result

No Comments

No Known Activations