INDEX

Explanations

LaTeX or coding commands used in document formatting

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

Personendaten

-0.68

-0.59

’

-0.56

 Roskov

-0.53

ыгана

-0.53

';

-0.52

 Spisak

-0.52

 Paglinawan

-0.51

OGND

-0.51

_);

-0.50

POSITIVE LOGITS

 doubtnut

0.83

Efq

0.82

 myſelf

0.78

 whoſe

0.71

 ſeveral

0.70

Eſ

0.69

 faſt

0.67

 beſt

0.67

migrationBuilder

0.67

Activations Density 0.060%

LaTeX or coding commands used in document formatting

No Comments

No Known Activations