INDEX

Explanations

references to specific programming structures or imports

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

"from" or "include" keywords

np_acts-logits-general · gemini-2.0-flash

code imports and includes

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

 photolibrary

-0.96

 ControllerBase

-0.89

 cdti

-0.88

 Audiodateien

-0.85

DockStyle

-0.84

 isComment

-0.84

DoubleQuotes

-0.83

ExecuteReader

-0.83

 Parcelable

-0.81

 itſelf

-0.80

POSITIVE LOGITS

testing

0.49

↵↵

0.48

 other

0.46

 testing

0.44

 Other

0.44

 static

0.42

its

0.41

static

0.41

We

0.40

Activations Density 0.043%

references to specific programming structures or imports

"from" or "include" keywords

code imports and includes

No Comments

No Known Activations