INDEX

Explanations

dates and numerical references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

".$_

-0.64

"%(

-0.60

Bur

-0.59

"=>$

-0.56

"=>"

-0.55

')}}"

-0.55

"");

-0.54

']).

-0.53

nameLabel

-0.53

étaient

-0.53

POSITIVE LOGITS

 Normdatei

0.81

 snippetHide

0.75

 estekak

0.72

 Sienna

0.67

PositiveButton

0.67

Abr

0.64

 Drapeau

0.64

تفصیلات

0.64

︎

0.64

 Elsie

0.63

Activations Density 0.091%

dates and numerical references

No Comments

No Known Activations