INDEX

Explanations

references to the length of discussions or narratives

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

 призна

-0.79

 Joint

-0.46

ContentLoaded

-0.45

am

-0.43

weiler

-0.42

com

-0.41

 назна

-0.40

Nim

-0.40

↵↵

-0.40

Am

-0.40

POSITIVE LOGITS

 ilustracja

0.66

 wikipagina

0.65

ArgumentParser

0.62

 miniaturka

0.61

parsedMessage

0.61

RenderAtEndOf

0.59

 desmotivaciones

0.57

 Wikiseite

0.56

 fotografico

0.55

 bluzka

0.54

Activations Density 0.013%

references to the length of discussions or narratives

No Comments

No Known Activations