INDEX

Explanations

patterns in programming function definitions 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-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rospy

-0.46

yarnpkg

-0.36

ANTLR

-0.36

bcrypt

-0.35

 gynhyrchwyd

-0.35

 intptr

-0.35

 işte

-0.34

adaptiveStyles

-0.34

 Picchu

-0.34

VolleyError

-0.34

POSITIVE LOGITS

 تضيفلها

0.72

 nahilalakip

0.54

出版年

0.52

DebuggerNonUser

0.52

قایناقلار

0.50

httphttps

0.50

ViewFeatures

0.46

UnsafeEnabled

0.46

UnknownFieldSet

0.46

ValueGenerated

0.44

Activations Density 0.012%

patterns in programming function definitions and structure

No Comments

No Known Activations