INDEX

Explanations

phrases indicating importance or significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 megjelen

-0.48

foglal

-0.44

izadores

-0.44

eschön

-0.43

zugehen

-0.42

 menengah

-0.42

adeloupe

-0.42

atemala

-0.41

nalpot

-0.41

 tiks

-0.41

POSITIVE LOGITS

oneof

0.83

 another

0.68

another

0.66

among

0.64

GEBURTSDATUM

0.62

 أحد

0.61

 among

0.61

 Einer

0.60

one

0.59

 ANOTHER

0.58

Activations Density 0.106%

phrases indicating importance or significance

No Comments

No Known Activations