INDEX

Explanations

instances of negative sentiments or criticisms

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

stateMutability

-0.38

ußer

-0.38

 fakta

-0.38

Попис

-0.38

isième

-0.36

 &___

-0.36

 يتيمه

-0.35

urum

-0.35

ztyn

-0.35

࿔

-0.35

POSITIVE LOGITS

 disambiguazione

0.57

 مشين

0.44

 виправивши

0.40

seck

0.40

[@"

0.39

 الرياضيه

0.39

ghest

0.39

ibrill

0.39

 librarians

0.38

DrawerToggle

0.38

Activations Density 0.004%

instances of negative sentiments or criticisms

No Comments

No Known Activations