INDEX

Explanations

references to specific people, organizations, and places in a political or social context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

NOPQRST

-0.86

InjectAttribute

-0.81

InstrumentedTest

-0.75

 الحره

-0.74

">//

-0.74



-0.72

 الدولى

-0.71

FailureListener

-0.71

存于互联网档案馆

-0.68

msgTypes

-0.68

POSITIVE LOGITS

 anything

0.50

 known

0.48

 famously

0.46

 отношению

0.46

RenderAtEndOf

0.45

 anywhere

0.44

lov

0.43

 ever

0.43

 typically

0.41

 which

0.40

Activations Density 1.167%

references to specific people, organizations, and places in a political or social context

No Comments

No Known Activations