INDEX

Explanations

references to locking mechanisms, particularly in relation to screens and instructions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rendus

-0.82

 Bevan

-0.81

twimg

-0.80

 therefrom

-0.79

 normaux

-0.77

PRD

-0.76

ValueStyle

-0.76

 profonde

-0.75

 piratas

-0.75

CBR

-0.75

POSITIVE LOGITS

 locks

1.50

 Locks

1.49

 LOCK

1.48

Locks

1.48

 lock

1.47

 Lock

1.42

locks

1.31

LOCK

1.27

 Lockwood

1.26

lock

1.26

Activations Density 0.072%

references to locking mechanisms, particularly in relation to screens and instructions

No Comments

No Known Activations