INDEX

Explanations

geographical locations and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

StoryboardSegue

-0.71

 consulate

-0.57

 Consulate

-0.53

 Marathi

-0.53

transQ

-0.53

 Gerard

-0.52

 Gerrard

-0.51

 Durban

-0.50

</thead>

-0.50

 IndexPath

-0.49

POSITIVE LOGITS

 Canberra

1.21

 Capital

1.16

 capital

1.07

Capital

1.06

 Ottawa

1.04

 CAPITAL

1.02

 Delhi

0.99

 Abuja

0.97

 capitale

0.94

CAPITAL

0.94

Activations Density 0.121%

geographical locations and institutions

No Comments

No Known Activations