INDEX

Explanations

instances of the word "appear" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 esfor

-0.77

("/{

-0.68

keyCode

-0.67

NAD

-0.67

<h2>

-0.66

Cox

-0.64

 entscheid

-0.63

idazole

-0.63

робнее

-0.62

 Huber

-0.62

POSITIVE LOGITS

 appear

1.52

 Appear

1.50

 appearances

1.44

 appearance

1.43

pearing

1.40

 Appears

1.37

 appearing

1.37

 appears

1.37

Appear

1.36

 appeared

1.34

Activations Density 0.087%

instances of the word "appear" and its variations

No Comments

No Known Activations