INDEX

Explanations

terminology related to shifts and change

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

selho

-0.73

 dach

-0.67

AfterEach

-0.65

 Dmit

-0.65

nmgp

-0.65

Chooser

-0.65

 Cochran

-0.64

 bParam

-0.63

eau

-0.61

GAL

-0.59

POSITIVE LOGITS

 Shifts

1.34

 shifts

1.27

shifted

1.24

shifts

1.24

 SHIFT

1.19

 shift

1.19

hift

1.16

 Shift

1.14

shift

1.09

 Shirts

1.08

Activations Density 0.139%

terminology related to shifts and change

No Comments

No Known Activations