INDEX

Explanations

technical terms and references related to programming and data structures

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

RTEX

-0.46

writeFieldEnd

-0.46

OGND

-0.42

]),

-0.41

 AssemblyCulture

-0.41

msgid

-0.41

 NSCoder

-0.40

 Chwiliwch

-0.40

}}_

-0.40

 autorytatywna

-0.39

POSITIVE LOGITS

MethodManager

0.43

IndentedString

0.43

postsleuth

0.42

 majeurs

0.42

osoba

0.41

iettivo

0.40

ocrat

0.40

AddTagHelper

0.39

REGULAR

0.39

outine

0.39

Activations Density 0.951%

technical terms and references related to programming and data structures

No Comments

No Known Activations