INDEX

Explanations

text that discusses review processes and methodologies in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 resourceCulture

-0.95

UnusedPrivate

-0.66

Personensuche

-0.63

Rüyada

-0.63

 समीक्षक

-0.62

 NDEBUG

-0.61

formik

-0.60

 AssemblyCulture

-0.59

expandindo

-0.57

biamo

-0.56

POSITIVE LOGITS

how

0.69

arounds

0.66

 فريبيس

0.61

 briefly

0.60

why

0.59

 discusses

0.58

 examples

0.57

examples

0.54

 discuss

0.53

 explains

0.53

Activations Density 0.358%

text that discusses review processes and methodologies in research

No Comments

No Known Activations