INDEX

Explanations

the word "just"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

 just

-0.73

MLLoader

-0.56

just

-0.55

 Just

-0.53

Just

-0.52

batore

-0.51

 teck

-0.49

 some

-0.49

 this

-0.48

gapan

-0.47

POSITIVE LOGITS

MigrationBuilder

0.86

 AssemblyCulture

0.80

 <<<<<<<<<<<<<<

0.73

]='\

0.73

AsUp

0.73

lenir

0.69

*/].

0.69

$_"

0.65

Efq

0.63

LogFactory

0.63

Activations Density 0.036%

the word "just"

No Comments

No Known Activations