INDEX

Explanations

numeric or coded data points within a given context

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

Numbers within dollar signs

np_acts-logits-general · gemini-2.0-flash

numerical coordinates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Six

-1.79

Six

-1.65

six

-1.53

SIX

-1.51

SIX

-1.50

 Sixteen

-1.48

 Twelve

-1.46

 sixteen

-1.42

six

-1.41

 twelve

-1.37

POSITIVE LOGITS

 preuves

0.49

 bancaire

0.47

 manières

0.45

 attentes

0.45

 modalités

0.44

 banques

0.43

 magnético

0.42

Koko

0.42

 travailleurs

0.41

 académico

0.41

Activations Density 0.268%

numeric or coded data points within a given context

Numbers within dollar signs

numerical coordinates

No Comments

No Known Activations