INDEX

Explanations

references to specific scientific journals and coding elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

dx

-0.58

dx

-0.56

Buildable

-0.49

 beginnetje

-0.49

-0.48

 campionato

-0.48

Dx

-0.48

 greu

-0.47

ax

-0.46

spraak

-0.46

POSITIVE LOGITS

tagHelper

0.98

TagHelper

0.83

Fence

0.70

DispatchToProps

0.70

modelBuilder

0.70

 Blanket

0.69

 velg

0.68

etheless

0.67

 Fencing

0.67

itars

0.67

Activations Density 2.026%

references to specific scientific journals and coding elements

No Comments

No Known Activations