INDEX

Explanations

mentions of artists

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

さん

-1.51

さんの

-1.27

enderror

-1.14

さんも

-0.99

さんが

-0.99

さんは

-0.98

さんに

-0.97

さんを

-0.93

さんと

-0.90

webElementXpaths

-0.89

POSITIVE LOGITS

dịch

0.63

 Anſ

0.61

 itſelf

0.60

 Carden

0.59

्ला

0.58

(++

0.58

 Económica

0.56

 Schenk

0.55

 Initially

0.54

 selectAll

0.52

Activations Density 0.006%

mentions of artists

No Comments

No Known Activations