INDEX

Explanations

terms related to control and regulation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lèvres

-0.69

 datter

-0.69

 Ibero

-0.66

WEEN

-0.65

ης

-0.64

 Mendez

-0.63

 Akade

-0.62

Jé

-0.62

DATASET

-0.62

 graines

-0.61

POSITIVE LOGITS

 Control

1.47

 control

1.47

 CONTROL

1.47

 controls

1.43

 Controls

1.41

Control

1.36

control

1.36

 FormControl

1.27

CONTROL

1.27

Controlling

1.20

Activations Density 0.083%

terms related to control and regulation

No Comments

No Known Activations