INDEX

Explanations

references to formal statements or announcements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

complexContent

-0.69

CppMethod

-0.67

 Reverso

-0.66

roek

-0.62

 فريبيس

-0.60

 مشين

-0.60

 Maulana

-0.58

 PLWABN

-0.58

 privatisation

-0.57

ыгана

-0.57

POSITIVE LOGITS

MergeFrom

0.52

eavor

0.51

 favor

0.48

 FAVOR

0.46

/*

0.46

 favorable

0.45

 exécu

0.45

ittle

0.45

 conseguenza

0.45

 насељу

0.44

Activations Density 0.042%

references to formal statements or announcements

No Comments

No Known Activations