INDEX

Explanations

instances of document structure and formatting instructions, specifically identifying the beginning of a new segment or section

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

XML string attributes

np_acts-logits-general · gemini-2.0-flash

string name

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

windowFixed

-0.81

ViewFeatures

-0.81

 <=",

-0.78

SharedCtor

-0.75

 ControllerBase

-0.74

InitVars

-0.74

 mergeFrom

-0.70

 OFDb

-0.70

 oprot

-0.68

Personendaten

-0.67

POSITIVE LOGITS

translation

1.19

 type

0.60

numerusform

0.59

Translation

0.54

bibfield

0.53

type

0.53

corresponding

0.50

lational

0.50

GJ

0.50

NewLabel

0.50

Activations Density 0.015%

instances of document structure and formatting instructions, specifically identifying the beginning of a new segment or section

XML string attributes

string name

No Comments

No Known Activations