INDEX

Explanations

technical terms and identifiers associated with programming, particularly related to device drivers 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

Boc

-0.39

xsd

-0.35

tho

-0.34

 actual

-0.34

Selfer

-0.34

tritts

-0.34

TypedDataSet

-0.34

niczy

-0.33

 favorite

-0.33

 JPanel

-0.33

POSITIVE LOGITS

:+:

0.67

########.

0.67

 pulumi

0.63

twimg

0.58

 disambiguazione

0.58

AddHtmlAttribute

0.57

rrggbb

0.56

 HttpNotFound

0.56

tinyos

0.56

parsedMessage

0.54

Activations Density 1.529%

technical terms and identifiers associated with programming, particularly related to device drivers and data structures

No Comments

No Known Activations