INDEX

Explanations

keywords related to events, terms, or cases that suggest specific attributes or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Monfieur

-0.60

elfare

-0.53

Efq

-0.52

 pleaſure

-0.52

 Romains

-0.50

ressee

-0.48

 ſtate

-0.47

 uſed

-0.47

 poffe

-0.46

Eſ

-0.45

POSITIVE LOGITS

httphttps

0.96

contentLoaded

0.96

 NSCoder

0.84

ThroughAttribute

0.78

 autorytatywna

0.75

Хьажоргаш

0.74

 ostavi

0.71

ViewFeatures

0.70

ItemLayout

0.70

AsUp

0.70

Activations Density 0.337%

keywords related to events, terms, or cases that suggest specific attributes or qualities

No Comments

No Known Activations