INDEX

Explanations

terms related to "MOR" or morphological concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 חיצוניים

-0.35

 تک

-0.34

セッション

-0.34

 /\.(

-0.33

 paralelo

-0.33

EXCHANGE

-0.32

確かに

-0.32

 Repeat

-0.32

 Regret

-0.31

Inggris

-0.31

POSITIVE LOGITS

Mor

0.96

Mor

0.92

mor

0.84



0.83

MOR

0.79

mor

0.76

MOR

0.72

 estekak

0.63

 typelib

0.62

 informée

0.61

Activations Density 0.107%

terms related to "MOR" or morphological concepts

No Comments

No Known Activations