INDEX

Explanations

mentions of software features and functionalities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 features

-1.11

features

-0.99

 Features

-0.96

 feature

-0.89

Features

-0.89

 FEATURES

-0.85

feature

-0.78

 Feature

-0.76

Feature

-0.74

FEATURES

-0.74

POSITIVE LOGITS

Transkript

0.55

 geweest

0.48

InSection

0.47

 purpoſe

0.47

 astore

0.46

enumi

0.46

findpost

0.45

 ModelRenderer

0.44

 Conſ

0.44

Gemeinden

0.43

Activations Density 0.013%

mentions of software features and functionalities

No Comments

No Known Activations