INDEX

Explanations

character names and terms in various languages, particularly those with diacritics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 المعيارى

-0.75

<strong>

-0.65

ule

-0.62

 похо

-0.61

almaz

-0.61

-0.60

<h2>

-0.60

oid

-0.60

 access

-0.59

もら

-0.59

POSITIVE LOGITS

 Beyoncé

0.88

 Erdoğan

0.86

 Citroën

0.85

Rüyada

0.85

 Bogotá

0.84

 Nestlé

0.84

 doughnuts

0.84



0.82

 Condé

0.82

hitheatre

0.81

Activations Density 0.479%

character names and terms in various languages, particularly those with diacritics

No Comments

No Known Activations