INDEX

Explanations

phrases indicating frequency or commonality in behaviors or characteristics

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

 possibly

-1.08

possibly

-0.95

 potentially

-0.94

 conceivably

-0.89

 möglicherweise

-0.89

potentially

-0.88

 posiblemente

-0.86

 Possibly

-0.81

Possibly

-0.79

 apparently

-0.76

POSITIVE LOGITS

 suele

0.87

 Either

0.84

Either

0.83

 brukar

0.81

 either

0.80

 suelen

0.79

bý

0.78

 nowadays

0.73

 entweder

0.72

accompanied

0.72

Activations Density 0.469%

phrases indicating frequency or commonality in behaviors or characteristics

No Comments

No Known Activations