INDEX

Explanations

phrases indicating spatial relationships, particularly those involving "inside."

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

ventional

-0.70

HasKey

-0.69

REEK

-0.67

 Sera

-0.66

лару

-0.66

apunov

-0.66

ambung

-0.65

 Mawr

-0.65

cillor

-0.64

pulumi

-0.64

POSITIVE LOGITS

 Inside

1.61

Inside

1.52

 INSIDE

1.50

inside

1.45

 inside

1.42

INSIDE

1.38

 InputDecoration

1.32

 Dentro

1.07

 Outside

1.03

OUTSIDE

1.02

Activations Density 0.065%

phrases indicating spatial relationships, particularly those involving "inside."

No Comments

No Known Activations