INDEX

Explanations

numeric representations of measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

reportWebVitals

-0.82

Referencies

-0.70

berday

-0.65

 ་་

-0.65

 Ephe

-0.64

PerformLayout

-0.63

спонд

-0.62

 للاسماء

-0.61

 incomplète

-0.61

 Ordovician

-0.60

POSITIVE LOGITS

IPLE

0.70

 triple

0.69

 threefold

0.58

 double

0.56

triple

0.56

ostar

0.55

кратно

0.54

\/

0.52

Erfolge

0.51

fold

0.51

Activations Density 0.306%

numeric representations of measurements or quantities

No Comments

No Known Activations