INDEX

Explanations

phrases related to visibility or perception

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bezeichneter

-0.82

 loisirs

-0.79

@"/

-0.78

 universitarios

-0.74

knapp

-0.73

 lunghi

-0.72

 Poehler

-0.72

 Hofmann

-0.71

unately

-0.69

Grath

-0.69

POSITIVE LOGITS

 Sees

1.70

 sees

1.67

see

1.56

saw

1.54

 seen

1.52

SEE

1.48

 SEEN

1.45

See

1.44

Saw

1.43

 Seen

1.42

Activations Density 0.151%

phrases related to visibility or perception

No Comments

No Known Activations