INDEX

Explanations

terms and concepts related to educational programs and projects

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

ViewImports

-0.54

 AssemblyCulture

-0.48

ApiModelProperty

-0.47

InlineData

-0.47

MergeFrom

-0.46

älde

-0.43

PullParser

-0.43

 jadx

-0.42

usercontent

-0.42

autogui

-0.42

POSITIVE LOGITS

rungsseite

0.54

SourceChecksum

0.50

 Roskov

0.47

principalColumn

0.44

 Inscrivez

0.44

 mecánico

0.41

SequentialGroup

0.41

 myſelf

0.40

 تضيفلها

0.39

 Houſe

0.39

Activations Density 1.734%

terms and concepts related to educational programs and projects

No Comments

No Known Activations