INDEX

Explanations

text discussing common practices, features, and occurrences in various contexts

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

prevalence or commonness

np_acts-logits-general · gemini-2.0-flash

common occurrence or practice

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

 للاسماء

-0.57

()]);

-0.54

FormTagHelper

-0.51

makeConstraints

-0.48

mml

-0.47

CGI

-0.44

 Standing

-0.43

enumii

-0.43

TORE

-0.43

unch

-0.42

POSITIVE LOGITS

 commonly

0.66

bootstrapcdn

0.66

 common

0.65

 BorderRadius

0.63

common

0.61

 happening

0.61

 común

0.60

commonly

0.58

 Happens

0.57

 durchaus

0.57

Activations Density 0.643%

text discussing common practices, features, and occurrences in various contexts

prevalence or commonness

common occurrence or practice

No Comments

No Known Activations