INDEX

Explanations

names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/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.12.hook_resid_post

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

InputGroup

-0.71

 Svar

-0.69

 Mercer

-0.68

Pivot

-0.68

 Pust

-0.67

 Pivot

-0.66

 surfactant

-0.66

 religieuses

-0.66

耕

-0.65

Piv

-0.64

POSITIVE LOGITS

#+#

0.79

featureID

0.75

 OkHttpClient

0.73

 Seligman

0.71

Toni

0.70

 Himo

0.69

 Snapdragon

0.68

getDrawable

0.66

 Zidane

0.65

évaluateur

0.65

Activations Density 0.220%

names of people and places

No Comments

No Known Activations