INDEX

Explanations

references to floors in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 acte

-0.77

pè

-0.75

多い

-0.72

벳

-0.72

matitis

-0.70

 newVal

-0.69

../../

-0.69

 Königreich

-0.69

 Houd

-0.69

 Pics

-0.68

POSITIVE LOGITS

 floor

1.47

 floors

1.46

 Floor

1.45

 FLOOR

1.39

 Floors

1.34

FLOOR

1.32

floor

1.29

Floor

1.28

floors

1.26

 flooring

1.11

Activations Density 0.080%

references to floors in various contexts

No Comments

No Known Activations