INDEX

Explanations

phrases that introduce a subject or topic for discussion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Referanser

-0.62

انيف

-0.57

最初は

-0.54

after

-0.52

 сначала

-0.47

SequentialGroup

-0.47

estar

-0.47

ssos

-0.45

vend

-0.45

 ventre

-0.44

POSITIVE LOGITS

 riguarda

0.83

IntoConstraints

0.79

 regard

0.73

 estimés

0.72

 Infórmanos

0.72

dientemente

0.69

 Мексичка

0.69

 regards

0.68

 nahilalakip

0.68

KommentareTeilen

0.66

Activations Density 0.130%

phrases that introduce a subject or topic for discussion

No Comments

No Known Activations