INDEX

Explanations

code-related terminology and structure

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

 GenerationType

-0.47

Subviews

-0.46

 متعلقه

-0.43

 ModelRenderer

-0.43

 IndexPath

-0.42

Statistiche

-0.41

 فريبيس

-0.41

uinal

-0.41

simpleType

-0.40

jangkau

-0.39

POSITIVE LOGITS

 tartalomajánló

0.47

 محفوظة

0.45

RTEE

0.39

 marginBottom

0.38

borderBottom

0.36

CopyWith

0.36

 față

0.35

Билгалдахарш

0.35

XX

0.35

paddingRight

0.35

Activations Density 0.229%

code-related terminology and structure

No Comments

No Known Activations