INDEX

Explanations

specific tokens or formatting patterns, likely indicating a programming or technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 payé

-0.55

Ecc

-0.50

 millions

-0.50

-------

-0.50

 palvel

-0.49

Equ

-0.48

OTIC

-0.48

mari

-0.46

 těchto

-0.46

anhão

-0.45

POSITIVE LOGITS

awtextra

0.91

 typelib

0.73

IsMutable

0.73

BeginInit

0.70

 CreateTagHelper

0.66

 BoxDecoration

0.63

gemäß

0.62

ValueStyle

0.58

ыгана

0.58

وحة

0.57

Activations Density 0.068%

specific tokens or formatting patterns, likely indicating a programming or technical context

No Comments

No Known Activations