INDEX

Explanations

numerical data or values

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PyExc

-0.47

Diweddarwch

-0.47

 MainAxisSize

-0.46

 nahilalakip

-0.44

UnusedPrivate

-0.41

WireFormat

-0.40

ReusableCell

-0.39

сторі

-0.39

setVerticalGroup

-0.39

AtIndexPath

-0.39

POSITIVE LOGITS

HtmlAttribute

0.42

PostExecute

0.41

 addSubview

0.41

gesellschaft

0.41

GraphicsUnit

0.40

 الحره

0.40

 Roof

0.39

URLException

0.39

Roof

0.39

 ErrIntOverflow

0.38

Activations Density 0.000%

numerical data or values

No Comments

No Known Activations