INDEX

Explanations

phrases related to data analysis and scientific insights

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

LookAnd

-0.71

tagHelperRunner

-0.71

RegressionTest

-0.69

PhysRev

-0.67

SPATH

-0.62

URLException

-0.58

 Вікіпе

-0.57

Sklici

-0.54

enterOuterAlt

-0.54

AppMethodBeat

-0.54

POSITIVE LOGITS

 revealing

1.25

 informative

1.20

 insights

1.20

 clues

1.13

 insight

1.13

 helps

1.13

 useful

1.12

 helpful

1.11

 reveal

1.10

 reveals

1.08

Activations Density 0.972%

phrases related to data analysis and scientific insights

No Comments

No Known Activations