INDEX

Explanations

positive descriptors and evaluations of experiences or people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

chao

-0.50

Endless

-0.47

 breathtaking

-0.45

 incompar

-0.45

 boundless

-0.45

 utterly

-0.44

endless

-0.44

 anymore

-0.44

 getItemCount

-0.44

UTELY

-0.43

POSITIVE LOGITS

 CreateTagHelper

1.09

PerformLayout

1.06

 disambiguazione

0.93

 autorytatywna

0.85

 defaultstate

0.83

 فريبيس

0.78

SequentialGroup

0.78

 Waray

0.78

存于互联网档案馆

0.77

 متعلقه

0.76

Activations Density 0.176%

positive descriptors and evaluations of experiences or people

No Comments

No Known Activations