INDEX

Explanations

references to the name "Kosuke."

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

ClientSize

-0.71

 Púb

-0.68

 mola

-0.68

########.

-0.66

hetamine

-0.65

 auffi

-0.65

TagHelper

-0.64

chieben

-0.63

depart

-0.63

 mide

-0.63

POSITIVE LOGITS

0.98

antaranya

0.69

Hauptartikel

0.68

 stessi

0.67

ses

0.67

 szükség

0.66

følgelig

0.66

ConstraintMaker

0.63

 necesar

0.63

 tartalmaz

0.61

Activations Density 0.016%

references to the name "Kosuke."

No Comments

No Known Activations