INDEX

Explanations

references to kitchen appliances or cooking utensils

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

 médical

-0.56

Da

-0.53

[]){

-0.52

ducation

-0.50

éraux

-0.48

 limp

-0.47

ته

-0.47

انه

-0.47

lid

-0.47

Da

-0.47

POSITIVE LOGITS

Espèce

0.68

 Gulch

0.59

ExtendWith

0.56

 LUMP

0.56

GTCX

0.55

 gynhyrchwyd

0.53

 uska

0.53

 للمعارف

0.52

TagHelpers

0.52

 AssemblyCompany

0.51

Activations Density 0.172%

references to kitchen appliances or cooking utensils

No Comments

No Known Activations