INDEX

Explanations

references to specific individuals or entities within a contextual framework

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

Citations starting with "@[A-Z]..."

np_acts-logits-general · gemini-2.0-flash

names and specific entities

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

 resourceCulture

-1.34

TypedDataSet

-1.03

Personendaten

-0.99

CppMethod

-0.96

 estekak

-0.95

 فريبيس

-0.95

RTLR

-0.94

enumii

-0.94

 disambiguazione

-0.94

Personensuche

-0.92

POSITIVE LOGITS

0.56

0.51

on

0.48

ing

0.47

an

0.47

in

0.46

0.45

le

0.45

Activations Density 0.506%

references to specific individuals or entities within a contextual framework

Citations starting with "@[A-Z]..."

names and specific entities

No Comments

No Known Activations

references to specific individuals or entities within a contextual framework

Citations starting with "@[A-Z]..."

names and specific entities

No Comments

No Known Activations