INDEX

Explanations

relationships and distinctions between individuals or entities, particularly with a focus on confusion or mistaken identity

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

namesake disambiguation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

 defaultstate

-0.68

MigrationBuilder

-0.67

LabelTagHelper

-0.58

ArrowToggle

-0.52

queryInterface

-0.51

OrNil

-0.50

PropertyChanging

-0.50

CodeAttribute

-0.48

TintMode

-0.47

ScopeManager

-0.46

POSITIVE LOGITS

 namesake

0.89

disambiguation

0.80

 unrelated

0.77

 acepción

0.66

 Vikipedi

0.63

 missp

0.61

ponym

0.61

 Namens

0.60

 gốc

0.59

 справ

0.59

Activations Density 0.191%

relationships and distinctions between individuals or entities, particularly with a focus on confusion or mistaken identity

namesake disambiguation

No Comments

No Known Activations