INDEX

Explanations

code-related syntax and structure, particularly around function definitions and variable assignments

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

 kasarigan

-0.60

 الحره

-0.50

principalColumn

-0.48

 AssemblyCompany

-0.47

 ब्रेकडाउन

-0.47

 становника

-0.46

writeFieldEnd

-0.44

 mapStateToProps

-0.43

 disambiguazione

-0.42

fortawesome

-0.41

POSITIVE LOGITS

 surla

0.51

">//

0.48

 exercices

0.43

 lesson

0.42

Ex

0.41

SequentialGroup

0.41

 explanation

0.40

lesson

0.40

daß

0.39

Ligações

0.39

Activations Density 0.011%

code-related syntax and structure, particularly around function definitions and variable assignments

No Comments

No Known Activations