INDEX

Explanations

attributes related to product features and efficiency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

'},

-0.80

 FormsModule

-0.75

 NgModule

-0.65

ITERATURE

-0.64

.},

-0.64

olesale

-0.64

}\]

-0.64

ientôt

-0.64

iffance

-0.63

isissez

-0.63

POSITIVE LOGITS

These

0.69

以上

0.65

 These

0.61

Etc

0.59

etc

0.54

Lähteet

0.53

などなど

0.53

以上の

0.53

 Référence

0.53

 <<<<<<<<<<<<<<

0.53

Activations Density 0.294%

attributes related to product features and efficiency

No Comments

No Known Activations