INDEX

Explanations

keywords related to important concepts or entities

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

"The [adjective] [noun]"

np_acts-logits-general · gemini-2.0-flash

key or main aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ExtendWith

-0.82

 kasarigan

-0.69

KommentareTeilen

-0.68

AxisAlignment

-0.64

gorithm

-0.61

хьтан

-0.61

Rhestr

-0.61

 समीक्षक

-0.61

 Normdatei

-0.60

TargetException

-0.59

POSITIVE LOGITS

key

1.32

 main

1.29

 primary

1.17

 cornerstone

1.17

 central

1.15

 major

1.15

 centerpiece

1.11

 principale

1.10

main

1.07

 core

1.05

Activations Density 0.320%

keywords related to important concepts or entities

"The [adjective] [noun]"

key or main aspects

No Comments

No Known Activations