INDEX

Explanations

information related to scientific measurements and comparisons

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

Portail

-0.89

TagMode

-0.83

expandindo

-0.78

tdessen

-0.77

anskje

-0.73

AnchorStyles

-0.72

instead

-0.69

 onCreateView

-0.67

 MainAxisSize

-0.65

 ujednoznacz

-0.65

POSITIVE LOGITS

 higher

1.08

Higher

0.91

higher

0.91

 Higher

0.86

Generally

0.86

 Generally

0.86

 lower

0.82

 larger

0.82

越是

0.81

 generally

0.80

Activations Density 0.471%

information related to scientific measurements and comparisons

No Comments

No Known Activations