INDEX

Explanations

phrases related to causation

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

Gruß

-0.82

Grüsse

-0.81

 Majefty

-0.79

 ſtate

-0.74

 Anſ

-0.74

Grüße

-0.71

 Shakspeare

-0.71

leſs

-0.70

 Chriftian

-0.70

citenamefont

-0.70

POSITIVE LOGITS

addGroup

0.91

div

0.83

ush

0.79

 Guides

0.63

addComponent

0.63

div

0.60

ol

0.55

ness

0.55

Guides

0.54

)|^{

0.54

Activations Density 0.149%

phrases related to causation

No Comments

No Known Activations