INDEX

Explanations

technical terminology related to data processing and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 épaules

-0.57

 bocca

-0.55

 istrinya

-0.54

Portale

-0.53

 poussière

-0.53

 prêtres

-0.53

 oreilles

-0.52

 genoux

-0.49

 fratelli

-0.48

 lèvres

-0.46

POSITIVE LOGITS

出版年

0.77

 numpy

0.76

PreAuthorize

0.74

Viitteet

0.71

Nx

0.68

 dataframe

0.68

UNTE

0.67

WritableDatabase

0.65

 ndarray

0.64

 lenker

0.63

Activations Density 1.133%

technical terminology related to data processing and transformation

No Comments

No Known Activations