INDEX

Explanations

inquiries or questions about topics or services

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

Questions starting with Q:

np_acts-logits-general · gemini-2.0-flash

what, how, or why questions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

TypedDataSet

-0.51

präche

-0.49

لبية

-0.48

yla

-0.45

toli

-0.43

ázquez

-0.42

muir

-0.42

SUM

-0.41

DetailView

-0.40

alon

-0.39

POSITIVE LOGITS

how

1.04

How

1.02

How

1.01

how

0.97

 What

0.96

What

0.96

 initComponents

0.94

why

0.93

Why

0.90

 what

0.86

Activations Density 0.301%

inquiries or questions about topics or services

Questions starting with Q:

what, how, or why questions

No Comments

No Known Activations