INDEX

Explanations

references to specific books and their authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

 liter

-0.47

MathML

-0.47

github

-0.46

buch

-0.46

hombo

-0.46

 onOptions

-0.45

 Fuller

-0.45

ˏ

-0.44

ayette

-0.42

 relatie

-0.41

POSITIVE LOGITS

 doInBackground

0.62

Jeografia

0.60

ïque

0.59

verwijspagina

0.59

expandindo

0.59

دانشنامهٔ

0.59

IntoConstraints

0.58

ंदीखरीदारी

0.58

 Conversions

0.57

Conversion

0.57

Activations Density 0.116%

references to specific books and their authors

No Comments

No Known Activations