INDEX

Explanations

references to "world" and related concepts

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

following "world"

np_acts-logits-general · gemini-2.0-flash

global scale and influence

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

SBATCH

-0.67

 تضيفلها

-0.64

webElementGuid

-0.60

مصادر

-0.60

rativo

-0.58

addPreferredGap

-0.58

RenderAtEndOf

-0.57

 oprot

-0.57

LIF

-0.57

PyExc

-0.56

POSITIVE LOGITS

WIDE

0.82

liness

0.75

Wide

0.74

 MainAxisSize

0.72

 Wide

0.69

 wide

0.67

views

0.66

 entier

0.64

🌍

0.56

各地

0.55

Activations Density 0.080%

references to "world" and related concepts

following "world"

global scale and influence

No Comments

No Known Activations