INDEX

Explanations

instances of repetition or iterative actions

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

Christy

-0.49

狂

-0.48

istici

-0.47

 combineReducers

-0.47

rosen

-0.46

volmente

-0.46

mability

-0.46

schild

-0.46

าสตร์

-0.45

indelijk

-0.45

POSITIVE LOGITS

 disambiguazione

1.01

 دیکھیے

0.86

homonymie

0.72

GOTREF

0.71

RunWith

0.69

 ISNI

0.67

transQ

0.67

yarnpkg

0.67

Personensuche

0.67

*++

0.65

Activations Density 0.065%

instances of repetition or iterative actions

No Comments

No Known Activations