INDEX

Explanations

references to game or position slots

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 صوتيه

-0.74

GEBURTSDATUM

-0.71

(!__

-0.65

="@+

-0.65

SOUNDBITE

-0.65

 mergeFrom

-0.64

SourceChecksum

-0.63

 Signalez

-0.63

 maternelle

-0.62

POSITIVE LOGITS

 slot

2.34

slot

2.21

 Slot

2.13

Slot

2.09

 slots

1.93

 SLOT

1.67

 Slots

1.65

SLOT

1.55

Slots

1.53

slots

1.45

Activations Density 0.061%

references to game or position slots

No Comments

No Known Activations