INDEX

Explanations

punctuation marks and numerical formats in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.62

postmedia

-0.57

in

-0.51

-0.50

bukkit

-0.49

 blancas

-0.48

 getConfig

-0.47

The

-0.46

 Friedens

-0.46

 breath

-0.45

POSITIVE LOGITS

CloseOperation

0.94

RenderAtEndOf

0.91

 esternos

0.89

 AssemblyCompany

0.82

 invokingState

0.80

contentLoaded

0.80

 ModelExpression

0.80

 kaarangay

0.80

 виправивши

0.77

 للاسماء

0.75

Activations Density 0.351%

punctuation marks and numerical formats in the text

No Comments

No Known Activations