INDEX

Explanations

elements related to warranties, updates, and support information

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

following commas

np_acts-logits-general · gemini-2.0-flash

all

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estekak

-0.69

GEBURTSDATUM

-0.66

principalColumn

-0.65

 Wicidata

-0.64

astéroïdes

-0.64

 vPvB

-0.63

\{\\

-0.58

 bParam

-0.57

oredCriteria

-0.57

webElementXpaths

-0.57

POSITIVE LOGITS

all

3.05

 allemaal

2.43

all

2.39

 semuanya

1.96

ALL

1.94

 semua

1.91

All

1.87

All

1.77

すべて

1.74

全て

1.70

Activations Density 0.952%

elements related to warranties, updates, and support information

following commas

all

No Comments

No Known Activations