INDEX

Explanations

references to quantities or distributions of groups in relation to various categories

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

Personensuche

-0.88

EDEFAULT

-0.87

 EconPapers

-0.86

AddTagHelper

-0.84

expandindo

-0.84

AndEndTag

-0.82

 autorytatywna

-0.81

rungsseite

-0.80

RenderAtEndOf

-0.78

يميديا

-0.77

POSITIVE LOGITS

0.37

↵↵

0.35

 flat

0.35

Dependency

0.29

 nast

0.29

 araba

0.29

sat

0.29

0.28

The

0.28

↵

0.28

Activations Density 0.092%

references to quantities or distributions of groups in relation to various categories

No Comments

No Known Activations