INDEX

Explanations

references to medical or health-related studies and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

kháu

-0.54

ifrance

-0.40

RenderAtEndOf

-0.39

Халык

-0.39

 solches

-0.38

นั้น

-0.36

CELLANEOUS

-0.36

buie

-0.36

 GIPHY

-0.34

(;;)

-0.34

POSITIVE LOGITS

who

4.25

who

2.98

 whom

2.89

 quien

2.78

Who

2.36

 quién

2.33

 quienes

2.31

whom

2.30

Who

2.30

 którzy

2.27

Activations Density 2.645%

references to medical or health-related studies and conditions

No Comments

No Known Activations