INDEX

Explanations

phrases that indicate nomenclature or definitions of terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

躇

-0.77

findpost

-0.59

%)$

-0.56

offsetof

-0.53

SOUNDBITE

-0.51

 intptr

-0.51

."]

-0.49

 pourtant

-0.49

vast

-0.47

}]$

-0.47

POSITIVE LOGITS

Personendaten

0.83

Datuak

0.81

<bos>

0.65

 propOrder

0.62

IContainer

0.60

WithMany

0.60

BufferException

0.60

GEBURTSDATUM

0.60

IBOutlet

0.58

 fusca

0.58

Activations Density 0.622%

phrases that indicate nomenclature or definitions of terms

No Comments

No Known Activations