INDEX

Explanations

technical terms and references related to coding and software errors

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

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

OGND

-0.75



-0.73

aarrggbb

-0.73

Personensuche

-0.69

+#+#

-0.68

ंदीखरीदारी

-0.67

 ſche

-0.65

expandindo

-0.64

Datuak

-0.63

Tikang

-0.63

POSITIVE LOGITS

sizePolicy

0.36

monary

0.32

...

0.32

 liền

0.31

便

0.31

error

0.31

zydent

0.31

exception

0.30

module

0.30

../../../

0.30

Activations Density 0.004%

technical terms and references related to coding and software errors

No Comments

No Known Activations