INDEX

Explanations

numerical data and statistical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 houſe

-0.65

 raiſ

-0.62

 itſelf

-0.62

 Inſ

-0.59

 pleaſure

-0.58

 laſt

-0.58

 himſelf

-0.58

yargs

-0.58

 fubject

-0.55

ITZER

-0.55

POSITIVE LOGITS

ergies

0.76

出版年

0.68

ramid

0.59

antMatchers

0.57

Geplaatst

0.56

VolleyError

0.55

astify

0.55

 cern

0.55

 مرئيه

0.54

ragalactic

0.52

Activations Density 0.391%

numerical data and statistical references

No Comments

No Known Activations