INDEX

Explanations

code structure and function definitions, particularly those associated with initialization and input/output handling

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

"init", "id", or "stdio" following code

np_acts-logits-general · gemini-2.0-flash

code initializers and ids

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 inelastic

-0.48

็ก

-0.46

 määrä

-0.44

setSelection

-0.42

fois

-0.42

 onStart

-0.41

 mieszkańców

-0.40

 associés

-0.40

atau

-0.39

POSITIVE LOGITS

 CreateTagHelper

5.78

SequentialGroup

1.43

FontStyle

1.36

__(/*!

1.14

ISupport

1.10

 فريبيس

1.06

ftagPool

1.05

@[+][

1.01

 للمعارف

1.00

ंदीखरीदारी

0.99

Activations Density 0.005%

code structure and function definitions, particularly those associated with initialization and input/output handling

"init", "id", or "stdio" following code

code initializers and ids

No Comments

No Known Activations