INDEX

Explanations

terms related to translation or transformation processes

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

 trans

-0.69

trans

-0.59

 Trans

-0.53

 transnational

-0.48

Trans

-0.47

 يتيمه

-0.46

🩺

-0.43

 tæn

-0.43

 Ahli

-0.42

 translocation

-0.41

POSITIVE LOGITS

setVerticalGroup

0.57

ResumeLayout

0.52

 AssemblyCompany

0.47

//

0.45

DockStyle

0.45

 otomatig

0.45

RegressionTest

0.41

नलिखित

0.40

///</

0.40

Демографія

0.39

Activations Density 0.000%

terms related to translation or transformation processes

No Comments

No Known Activations