INDEX

Explanations

references to publication or document identifiers in academic writing

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

[@ followed by a code]

np_acts-logits-general · gemini-2.0-flash

biological and technical terms

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

енча

-0.63

 Italijani

-0.59

 variété

-0.54

Portail

-0.53

árol

-0.52

 financière

-0.52

 médicale

-0.52

 assolu

-0.52

 stället

-0.52

 cérami

-0.51

POSITIVE LOGITS

tagHelper

2.24

ExecutionContext

0.93

TagHelpers

0.78

 ModelExpression

0.77

 оригіналу

0.67

jspx

0.65

LookAnd

0.64

webElementGuid

0.63

ThroughAttribute

0.62

GOTREF

0.62

Activations Density 0.032%

references to publication or document identifiers in academic writing

[@ followed by a code]

biological and technical terms

No Comments

No Known Activations