INDEX

Explanations

mentions of hidden layers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

MigrationBuilder

-0.99

 jspb

-0.85

 ExecuteAsync

-0.81

UserScript

-0.80

NamedQueries

-0.79

xaml

-0.79

Personensuche

-0.78

 OkHttpClient

-0.77

 caminhão

-0.77

DockStyle

-0.77

POSITIVE LOGITS

hidden

2.02

 Hidden

2.02

 hidden

2.01

Hidden

1.94

HIDDEN

1.77

 caché

1.17

 secret

1.14

 verborgen

1.13

 oculto

1.09

 invisible

1.09

Activations Density 0.053%

mentions of hidden layers in various contexts

No Comments

No Known Activations