INDEX

Explanations

punctuation marks and separators used in lists or to denote sections of text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

Personendaten

-0.44

twimg

-0.39

migrationBuilder

-0.39

aarrggbb

-0.39

༘

-0.38

 صوتيه

-0.35

 himo

-0.35

 fourrure

-0.35

wpi

-0.34

POSITIVE LOGITS

 nakalista

0.68

 propOrder

0.53

Попис

0.50

ressee

0.49

tdown

0.47

 Signalez

0.47

 Vign

0.47

erintah

0.46

still

0.46

FXMLLoader

0.46

Activations Density 3.414%

punctuation marks and separators used in lists or to denote sections of text

No Comments

No Known Activations