INDEX

Explanations

references to gold and its related terms

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

 béné

-0.59

chymal

-0.55

 brancas

-0.55

 péné

-0.54

 scolas

-0.54

 détru

-0.53

óp

-0.52

showError

-0.52

erent

-0.52

uvw

-0.51

POSITIVE LOGITS

 Gold

0.93

 GOLD

0.90

Gold

0.87

 plated

0.85

GOLD

0.84

 gold

0.83

 bullion

0.78

 medals

0.77

gold

0.77

 medal

0.76

Activations Density 0.089%

references to gold and its related terms

No Comments

No Known Activations