INDEX

Explanations

references to a specific pharmaceutical product or its variant names

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

TOUCH

-0.57

setopt

-0.56

 touch

-0.54

sire

-0.54

HasIndex

-0.54

})));

-0.53

 виправивши

-0.52

 Touch

-0.51

anyahu

-0.50

kloped

-0.50

POSITIVE LOGITS

Gal

0.80

GAL

0.78

Gal

0.75

gal

0.68

 Galile

0.63

gal

0.62

GAL

0.62

 Galli

0.58

 Galbraith

0.58

 Gallen

0.57

Activations Density 0.081%

references to a specific pharmaceutical product or its variant names

No Comments

No Known Activations