INDEX

Explanations

references to academic papers and studies related to specific findings or observations

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

followed by citations or references

np_acts-logits-general · gemini-2.0-flash

references to figures, papers, or sections

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ScopeManager

-0.75

RTEE

-0.70

RTLR

-0.68

الحياه

-0.67

estacks

-0.66

MLLoader

-0.66

Portale

-0.66

 незавершена

-0.65

 חיצוניים

-0.65

kháu

-0.65

POSITIVE LOGITS

addPreferredGap

0.36

 diritti

0.30

 peuples

0.29

 médicaux

0.28

ș

0.28

ViewChild

0.28

 orizz

0.27

 refusé

0.26

 plancher

0.26

we

0.26

Activations Density 2.083%

references to academic papers and studies related to specific findings or observations

followed by citations or references

references to figures, papers, or sections

No Comments

No Known Activations