INDEX

Explanations

proper nouns associated with famous individuals, brands, and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

rungsseite

-1.14

 autorytatywna

-1.12

 propOrder

-1.07

>{@

-1.07

SourceChecksum

-1.03

EndGlobalSection

-1.01

GEBURTSDATUM

-1.01

رشف

-0.96

Билгалдахарш

-0.95

الحياه

-0.95

POSITIVE LOGITS

 itself

0.50

 stesso

0.49

及其

0.48

’

0.45

 stessa

0.45

Pyx

0.45

 today

0.44

に限

0.44

0.41

Activations Density 0.838%

proper nouns associated with famous individuals, brands, and products

No Comments

No Known Activations