INDEX

Explanations

citations or references to individuals in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

weisungen

-0.47

gisi

-0.46

 comigo

-0.46

 halves

-0.45

ーズ

-0.45

 kuin

-0.44

 Generales

-0.44

Understanding

-0.43

 induction

-0.41

 personlig

-0.41

POSITIVE LOGITS

 незавершена

0.68

=$?

0.66

 Roskov

0.66

 Мексичка

0.66

 utafitiHapana

0.63

rungsseite

0.62

\}\\

0.62

ględ

0.60

 Савезне

0.60

requireNonNull

0.60

Activations Density 0.439%

citations or references to individuals in a research context

No Comments

No Known Activations