INDEX

Explanations

references to protective gear, specifically armor

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

OGND

-0.71

gameserver

-0.65

 veran

-0.59

Rüyada

-0.54

ila

-0.54

 QWidget

-0.53

BeginInit

-0.53

 копия

-0.53

msgs

-0.53

 Inversion

-0.52

POSITIVE LOGITS

 depart

0.99

 departing

0.97

 departs

0.95

 departed

0.95

 exit

0.94

 armor

0.91

 departure

0.82

armor

0.80

 departures

0.77

 goodbye

0.76

Activations Density 0.141%

references to protective gear, specifically armor

No Comments

No Known Activations