INDEX

Explanations

references to issues, problems, or troubleshooting in various contexts

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

loo

-0.46

MessageTagHelper

-0.45

がか

-0.43

DOM

-0.42

CLO

-0.41

CUP

-0.41

rete

-0.41

clo

-0.41

RTEX

-0.40

ValueStyle

-0.40

POSITIVE LOGITS

 للاسماء

0.46

 saites

0.45

 iconTwitter

0.42

igshid

0.40

InitStruct

0.40

estero

0.40

 llorar

0.40

 cellpadding

0.39

usepackage

0.39

findpost

0.38

Activations Density 0.722%

references to issues, problems, or troubleshooting in various contexts

No Comments

No Known Activations