INDEX

Explanations

words and concepts related to various types of interactions, relationships, and classifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

protoimpl

-0.45

væ

-0.44

 referenties

-0.44

SessionFactory

-0.43

Fal

-0.43

 ГА

-0.43

NameInMap

-0.42

umas

-0.42

Tracklist

-0.42

plus

-0.41

POSITIVE LOGITS

 defaultstate

0.56

RenderAtEndOf

0.48

 препратки

0.40

 <<<<<<<<<<<<<<

0.39

 مرئيه

0.38

Personendaten

0.37

AddTagHelper

0.36

 Exacts

0.36

FieldNumber

0.36

ंदीखरीदारी

0.35

Activations Density 0.045%

words and concepts related to various types of interactions, relationships, and classifications

No Comments

No Known Activations