INDEX

Explanations

references to features or attributes of physical structures or entities

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

interiority or being "inside"

np_acts-logits-general · gemini-2.0-flash

inside and interior

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

 ویکی‌پدیا

-0.68

########.

-0.64

 Waray

-0.64

 Vikipedi

-0.62

/*

-0.58

elemField

-0.57

AndPassword

-0.56

getSystemService

-0.54

ActionMode

-0.53

jectory

-0.53

POSITIVE LOGITS

 inside

3.43

 Inside

3.04

inside

3.02

Inside

3.00

 INSIDE

2.69

 internal

2.58

 interior

2.55

INSIDE

2.42

 внутри

2.38

 inner

2.30

Activations Density 0.633%

references to features or attributes of physical structures or entities

interiority or being "inside"

inside and interior

No Comments

No Known Activations