INDEX

Explanations

references to algorithms, processes, and techniques in data analysis or processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

FormTagHelper

-0.62

contentLoaded

-0.60

awtextra

-0.60

IsContent

-0.56

⟬

-0.55

tagHelperRunner

-0.55

 protoimpl

-0.54

 Audiodateien

-0.50

 Exactos

-0.50

➟

-0.49

POSITIVE LOGITS

новниш

0.40

 aking

0.38

 Norden

0.38

 hinweg

0.35

 utafitiHapana

0.35

 Schluß

0.35

querque

0.34

までも

0.34

 converse

0.33

ByPrimaryKey

0.32

Activations Density 1.715%

references to algorithms, processes, and techniques in data analysis or processing

No Comments

No Known Activations