INDEX

Explanations

regulatory decisions and their implications in various contexts

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

preceding consequences, actions, or markers

np_acts-logits-general · gemini-2.0-flash

marks an event

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 noqa

-0.71

principalColumn

-0.68

Дереккөздер

-0.65

Autoritní

-0.64

 costuma

-0.64

GraphicsUnit

-0.62

 Often

-0.61

Often

-0.61

CodeAttribute

-0.61

bý

-0.61

POSITIVE LOGITS

 marks

1.49

 mark

1.13

marks

1.12

 represents

1.07

 marking

1.04

 marked

1.03

 markiert

1.00

 MARKS

0.94

marking

0.93

 represent

0.89

Activations Density 0.477%

regulatory decisions and their implications in various contexts

preceding consequences, actions, or markers

marks an event

No Comments

No Known Activations