INDEX

Explanations

indicators of authorship or source attribution

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

AddTagHelper

-0.55

 kapturem

-0.53

mobileqq

-0.52

expandindo

-0.52

pgterms

-0.51

ceğine

-0.49

 smtplib

-0.48

 дописавши

-0.47

 Photocase

-0.47

новниш

-0.46

POSITIVE LOGITS

ResumeLayout

0.52

'{@

0.44

showthread

0.44

 AssemblyTitle

0.42

setObjectName

0.40

 Posted

0.40

 <<<<<<<<<<<<<<

0.39

 Spisak

0.37

 localObject

0.37

Paused

0.36

Activations Density 0.003%

indicators of authorship or source attribution

No Comments

No Known Activations