INDEX

Explanations

numerical values or statistics

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

 이상

-0.36

 olabilir

-0.35

 sự

-0.33

 gärna

-0.32

 нему

-0.32

Источники

-0.32

ducción

-0.32

로운

-0.32

 śmier

-0.31

POSITIVE LOGITS

GOTREF

0.75

expandindo

0.69

'{@

0.59

ſicht

0.57

 Wikimedijinoj

0.56

postIndex

0.56

iſchen

0.56

 AssemblyTitle

0.56

+#+#

0.55

RenderAtEndOf

0.54

Activations Density 0.210%

numerical values or statistics

No Comments

No Known Activations