INDEX

Explanations

HTML elements and formatting symbols

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

HTML or code greater than/less than signs

np_acts-logits-general · gemini-2.0-flash

HTML tags and symbols

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

-0.56

-0.49

 public

-0.48

—

-0.48

public

-0.47

ച്ച

-0.45

kon

-0.45

ண

-0.45

 Public

-0.44

///</

-0.44

POSITIVE LOGITS

Efq

0.98

 متعلقه

0.94

 الاطلاع

0.85

ագրություններ

0.84

HomeAsUpEnabled

0.83

 Réponses

0.83

 المعيارى

0.82

InputBorder

0.81

;;)

0.76

mergeFrom

0.76

Activations Density 0.084%

HTML elements and formatting symbols

HTML or code greater than/less than signs

HTML tags and symbols

No Comments

No Known Activations