INDEX

Explanations

occurrences of the word "posted" and related terms, indicating updates or entries

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

Билгалдахарш

-1.07

 autorytatywna

-0.92

COUVER

-0.91

oredCriteria

-0.84

 intptr

-0.81



-0.81

Datuak

-0.80

 Italijanski

-0.78

Искәрмәләр

-0.78

Personensuche

-0.76

POSITIVE LOGITS

 occhiali

0.57

 mahdol

0.53

 aveug

0.49

 caduta

0.47

 luoghi

0.47

acidade

0.47

 chré

0.46

 táctil

0.46

 relazioni

0.46

 médaille

0.46

Activations Density 0.025%

occurrences of the word "posted" and related terms, indicating updates or entries

No Comments

No Known Activations