INDEX

Explanations

references to a central or primary theme in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

️

-0.72

tinyos

-0.71

Oise

-0.70

 Fleck

-0.69

 polvere

-0.69



-0.69

 phénom

-0.68

 Svizzera

-0.66

 Kopp

-0.65

 numérique

-0.64

POSITIVE LOGITS

 Main

1.38

 MAIN

1.36

 main

1.35

MAIN

1.25

Main

1.22

mainWindow

1.10

 mains

1.09

getMain

1.07

 Mains

1.07

main

1.05

Activations Density 0.052%

references to a central or primary theme in various contexts

No Comments

No Known Activations