INDEX

Explanations

proper nouns, particularly geographical names and institutions

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

-0.64

کنون

-0.62

льевич

-0.59

-0.56

 suivante

-0.55

ViewFeatures

-0.55

 seguente

-0.54

 pubblici

-0.53

@[+][

-0.52

Omaha

-0.52

POSITIVE LOGITS

Efq

0.86

󠁢

0.82

 Савезне

0.80

 Beſ

0.78

########.

0.76

 ſever

0.73

 Quelles

0.72

 Anſ

0.72

tvguidetime

0.71

 downg

0.71

Activations Density 0.605%

proper nouns, particularly geographical names and institutions

No Comments

No Known Activations