INDEX

Explanations

terms related to literature and literary works

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

"Lit", "liter", or "literature"

np_acts-logits-general · gemini-2.0-flash

literature

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

IntoConstraints

-0.66

DMETHOD

-0.65

makeConstraints

-0.62

 XCTest

-0.61

 StatefulWidget

-0.61

batore

-0.58

HomeAsUpEnabled

-0.56

TestingModule

-0.56

 InputDecoration

-0.52

 članak

-0.51

POSITIVE LOGITS

期刊论文

0.67

OGND

0.64

\"");

0.61

lit

0.58

Portail

0.56

WriteTagHelper

0.56

LIT

0.56

 Liter

0.55

Lit

0.54

Activations Density 0.092%

terms related to literature and literary works

"Lit", "liter", or "literature"

literature

No Comments

No Known Activations