INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PropertyGroup

-0.58

complexContent

-0.53

 iprot

-0.53

\}$.

-0.52

 يتيمه

-0.52

Étymologie

-0.49

awaiter

-0.46

博士

-0.45

 \%}$

-0.45

 StatelessWidget

-0.45

POSITIVE LOGITS

Personendaten

0.68

 incomplète

0.67

UnknownFieldSet

0.61

 '\\;'

0.60

ViewImports

0.59

 autorytatywna

0.57

zbęd

0.57

 atenção

0.55

 Sapp

0.54

⤹

0.54

Activations Density 1.758%

mathematical symbols and notations

No Comments

No Known Activations