INDEX

Explanations

references to "novels" and "artificial" concepts or intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

lic

-0.71

 Kabel

-0.68

 kele

-0.67

tas

-0.67

tas

-0.66

,\

-0.66

former

-0.63

my

-0.63

لمين

-0.60

<u>

-0.60

POSITIVE LOGITS

 GenerationType

1.05

 nahilalakip

1.02

 Мексичка

0.98

◦

0.96

 spacy

0.95

ukone

0.92

 ་་

0.91

 Arno

0.90

gdx

0.90

"}")

0.89

Activations Density 0.338%

references to "novels" and "artificial" concepts or intelligence

No Comments

No Known Activations