INDEX

Explanations

programming-related keywords and method definitions

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.32.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

 ProtoMessage

-0.46

dispatchEvent

-0.40

يميديا

-0.39

 estimated

-0.39

estimated

-0.39

felizmente

-0.38

vart

-0.37

 Estimated

-0.36

ynchronously

-0.35

calculate

-0.35

POSITIVE LOGITS

 builder

0.84

 builders

0.73

 Builder

0.72

Builder

0.69

builder

0.65

builders

0.62

 Builders

0.60

 builds

0.57

 BUILD

0.57

Fluent

0.56

Activations Density 0.055%

programming-related keywords and method definitions

No Comments

No Known Activations