INDEX

Explanations

names of characters and their relationships in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

脚注の使い方

-0.72

ụy

-0.70

Marcos

-0.68

 Marín

-0.67

 Foxx

-0.66

resta

-0.66

 Walden

-0.66

 Barbour

-0.65

 Tsch

-0.64

escu

-0.64

POSITIVE LOGITS

ərbaycan

0.83

 referenties

0.81

WebVitals

0.74

 otomatig

0.71

JAMIN

0.66

 vroe

0.66

 getApplication

0.66

abetes

0.65

wijl

0.65

 Keenan

0.65

Activations Density 2.159%

names of characters and their relationships in a narrative context

No Comments

No Known Activations