INDEX

Explanations

references to specific geographic locations or infrastructure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

Portail

-0.51

ko

-0.48

feitura

-0.48

vedad

-0.46

 defaultstate

-0.46

iz

-0.45

 hemis

-0.44

 AssemblyTitle

-0.44

❉

-0.43

PropertyGroup

-0.43

POSITIVE LOGITS

 highway

0.72

号線

0.70

FontOfSize

0.67

 route

0.65

沿い

0.65

 виправивши

0.65

 highways

0.62

SequentialGroup

0.61

 Highway

0.61

 routes

0.61

Activations Density 0.433%

references to specific geographic locations or infrastructure

No Comments

No Known Activations