INDEX

Explanations

references to Google and its associated services or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

NUMX

-1.02

+#+#

-0.98

EDEFAULT

-0.96

ChildScrollView

-0.94

Efq

-0.92

 photolibrary

-0.90

 الدولى

-0.88

 cherchés

-0.86

 Forumite

-0.84

 JTextField

-0.84

POSITIVE LOGITS

Human

0.82

 Human

0.81

human

0.69

org

0.68

 HUMAN

0.60

0.58

0.57

HUMAN

0.56

ACCESS

0.55

com

0.54

Activations Density 0.393%

references to Google and its associated services or products

No Comments

No Known Activations