INDEX

Explanations

references to national organizations and institutions

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

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

InjectAttribute

-0.88

ValueStyle

-0.83

tagHelperRunner

-0.75

enumi

-0.74

EDEFAULT

-0.69

NameInMap

-0.69



-0.64

 Âge

-0.63

ReusableCell

-0.63

 surla

-0.62

POSITIVE LOGITS

istic

0.88

 parks

0.70

ities

0.69

ized

0.68

istically

0.66

 anthem

0.65

ization

0.64

Parks

0.59

 level

0.58

ised

0.56

Activations Density 0.068%

references to national organizations and institutions

No Comments

No Known Activations