INDEX

Explanations

instances of the word "it"

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-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

-0.54

 magist

-0.44

 spéciales

-0.43

↵

-0.43

replaceable

-0.43

 (€

-0.42

 opérateurs

-0.41

 impossível

-0.41

 colorido

-0.41

POSITIVE LOGITS

bibfield

0.96

\{\\

0.96

the

0.96

 Monfieur

0.95

EndInit

0.93

 nahilalakip

0.89

.";

0.88

"):

0.88

BibitemShut

0.88

setVerticalGroup

0.87

Activations Density 0.093%

instances of the word "it"

No Comments

No Known Activations