INDEX

Explanations

elements related to programming functions and variables

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

Boolean values or logic

np_acts-logits-general · gemini-2.0-flash

boolean values and keywords

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

-0.57

-0.54

-0.48

<sup>

-0.47

<eos>

-0.46

");

-0.45

zenta

-0.45

()];

-0.45

POSITIVE LOGITS

 CreateTagHelper

1.03

PerformLayout

0.96

 estekak

0.94

 Himo

0.92

Personensuche

0.86

脚注の使い方

0.86

 propOrder

0.83

abestanden

0.83

 مشين

0.82

 NSCoder

0.81

Activations Density 0.145%

elements related to programming functions and variables

Boolean values or logic

boolean values and keywords

No Comments

No Known Activations