INDEX

Explanations

terms related to mathematical or computational processes, specifically focusing on repetitions and averages

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

RTLR

-0.44

 Sieg

-0.36

WriteLiteral

-0.34

 Brag

-0.34

 ganas

-0.32

complexType

-0.32

DotNetBar

-0.32

gasse

-0.31

Bla

-0.31

 relativamente

-0.31

POSITIVE LOGITS

новниш

0.56

 jspb

0.52

 ujednoznacz

0.49

 Comprometido

0.48

errHandler

0.47

 Tutti

0.47

:✨

0.47

ChildScrollView

0.46

odyne

0.46

 throughout

0.45

Activations Density 1.027%

terms related to mathematical or computational processes, specifically focusing on repetitions and averages

No Comments

No Known Activations