INDEX

Explanations

terms related to extrapolation and related statistical concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

extrapolation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

AndEndTag

-0.60

-0.56

قایناق‌لار

-0.51

 propOrder

-0.49

 autorytatywna

-0.47

المناصب

-0.47

ngrx

-0.46

SharedCtor

-0.45

 CanadaChoose

-0.44

 nuvem

-0.44

POSITIVE LOGITS

 extrapolated

1.39

 extrapolation

1.38

polate

0.93

 extra

0.71

 extradition

0.69

Ext

0.69

 extensions

0.67

Ext

0.65

 extension

0.64

 EXTR

0.64

Activations Density 0.017%

terms related to extrapolation and related statistical concepts

extrapolation

No Comments

No Known Activations