INDEX

Explanations

specific references to items or structures related to algorithms or coding syntax

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

Follows single letters

np_acts-logits-general · gemini-2.0-flash

johnnies, NIC, KISS, BIO, NI, KI

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

 Marcela

-0.53

 Faure

-0.53

 Marcello

-0.52

 Wanderers

-0.51

 remand

-0.50

NavController

-0.50

 Therese

-0.50

 Overton

-0.49

 Auer

-0.48

 Maura

-0.48

POSITIVE LOGITS

Ri

0.73

hi

0.71

Ti

0.71

Ri

0.71

 Ciri

0.71

Ti

0.70

Bi

0.70

Bi

0.69

ri

0.69

Hi

0.69

Activations Density 1.744%

specific references to items or structures related to algorithms or coding syntax

Follows single letters

johnnies, NIC, KISS, BIO, NI, KI

No Comments

No Known Activations