INDEX

Explanations

references to scientific claims and their supporting details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

HomeAsUpEnabled

-0.53

isContained

-0.46

mergeFrom

-0.43

mybatisplus

-0.42

 للمعارف

-0.41

EFIAPI

-0.39

 contemporáneo

-0.39

WriteBarrier

-0.38

OrWhiteSpace

-0.36

hadiran

-0.36

POSITIVE LOGITS

новништво

0.54

fort

0.52

″]

0.50

RegressionTest

0.49

0.48

 EdgeInsets

0.48

Personendaten

0.47

wery

0.47

 colt

0.47

malink

0.47

Activations Density 1.077%

references to scientific claims and their supporting details

No Comments

No Known Activations