INDEX

Explanations

numerical codes and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

SequentialGroup

-0.96

Autoritní

-0.92

 ddelweddau

-0.88

 nahilalakip

-0.86

StreetMap

-0.85

oredCriteria

-0.85

 AssemblyCulture

-0.83

tanleria

-0.83

medriver

-0.83

GEBURTSDATUM

-0.82

POSITIVE LOGITS

BeginContext

0.52

طيع

0.49

McC

0.46

 szár

0.46

ljen

0.44

::_('

0.44

 Sén

0.44

ear

0.43

ējās

0.43

 samego

0.43

Activations Density 1.172%

numerical codes and values

No Comments

No Known Activations