INDEX

Explanations

numerical values and counts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AutoField

-0.54

twimg

-0.52

 faſt

-0.49

 sumpay

-0.48

 raiſ

-0.47

__).

-0.47

PMailer

-0.47

 diſt

-0.46

 viſ

-0.45

wiſe

-0.45

POSITIVE LOGITS

/**

0.51

TabIndex

0.47

setVerticalGroup

0.46

 Extensions

0.46

 Extension

0.45

rungsseite

0.44

0.43

XmlAccessorType

0.42

FieldOffsetTable

0.41

 Currently

0.41

Activations Density 0.001%

numerical values and counts

No Comments

No Known Activations