INDEX

Explanations

numerical data, specifically related to measurements and quantities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SceneManagement

-0.47

ln

-0.44

st

-0.42

lil

-0.40

St

-0.38

bou

-0.37

كن

-0.37

<eos>

-0.36

/**

-0.36

POSITIVE LOGITS

 Roskov

1.10

 Jefus

0.91

 themſelves

0.90

Efq

0.86

 متعلقه

0.85

 itſelf

0.84

WriteBarrier

0.84

 EconPapers

0.84

 Monfieur

0.83

 kasarigan

0.82

Activations Density 1.530%

numerical data, specifically related to measurements and quantities

No Comments

No Known Activations