INDEX

Explanations

URLs and API references related to media and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

原始内容存档于

-0.69

 numberOfRows

-0.66

GEBURTS

-0.64

::~

-0.62

OGND

-0.61

 recommandée

-0.60

principalColumn

-0.60

latego

-0.57

DECREF

-0.57

tuesday

-0.57

POSITIVE LOGITS

0.65

 esternos

0.56

 الدولى

0.54

 Masking

0.54

www

0.53

 незавершена

0.52

 abolition

0.51

 auricular

0.50

 ſame

0.49

 Espero

0.49

Activations Density 0.168%

URLs and API references related to media and documentation

No Comments

No Known Activations