INDEX

Explanations

references to data points or metrics in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

UrlResolution

-0.59

+#+

-0.57

webElement

-0.57

richTextPanel

-0.57

!*\

-0.56

ValueStyle

-0.55

InstrumentedTest

-0.54

 nakalista

-0.54

 queſta

-0.54

parsedMessage

-0.54

POSITIVE LOGITS

 consolid

0.31

lom

0.30

writeFieldEnd

0.29

 encar

0.29

 autorytatywna

0.28

MockMvc

0.28

 dwelling

0.28

 congr

0.28

godic

0.27

asker

0.27

Activations Density 0.370%

references to data points or metrics in a structured format

No Comments

No Known Activations