INDEX

Explanations

function return types indicating the completion of a task or process

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

Code, errors, and programming-related text

np_acts-logits-general · gemini-2.0-flash

programming code and Q&A forums

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

 onAnimation

-0.54

 Kaspar

-0.53

GTK

-0.52

{:.

-0.51

 risult

-0.51

 versace

-0.50

 moschino

-0.49

glTex

-0.49

`"

-0.49

 Âge

-0.49

POSITIVE LOGITS

ISupport

0.69

 kasarigan

0.69

principalTable

0.62

 ویکی‌پدی

0.62

帖最后由

0.61

 Италијани

0.60

Collegamenti

0.59

ResponseWriter

0.59

 مرئيه

0.58

artin

0.58

Activations Density 0.085%

function return types indicating the completion of a task or process

Code, errors, and programming-related text

programming code and Q&A forums

No Comments

No Known Activations