INDEX

Explanations

references to mathematical symbols and terms commonly used in scientific equations or theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

NEC

-0.71

Demografía

-0.70

ibouti

-0.66

remadura

-0.66

Filler

-0.65

 Brito

-0.64

 borsa

-0.64

NEC

-0.61

 referenties

-0.61

yid

-0.60

POSITIVE LOGITS

 שוליים

0.88

raisemb

0.74

 désol

0.68

 iParam

0.68

 Seel

0.66

 Auro

0.66

.');

0.66

 Flair

0.65

Byd

0.65

GAT

0.64

Activations Density 0.447%

references to mathematical symbols and terms commonly used in scientific equations or theories

No Comments

No Known Activations