INDEX

Explanations

references to specific individuals and organizations related to the content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

COX

-0.81

XtraGrid

-0.80

 Yeti

-0.77

 Kupfer

-0.74

 Petr

-0.72

 parker

-0.71

anx

-0.69

apd

-0.69

Xml

-0.69

adpleegd

-0.69

POSITIVE LOGITS

Saul

0.71

RoutingModule

0.69

KERN

0.69

Calla

0.69

Coh

0.68

 Sali

0.67

rawtypes

0.67

TabStop

0.65

 Brig

0.65

usuf

0.65

Activations Density 1.306%

references to specific individuals and organizations related to the content

No Comments

No Known Activations