INDEX

Explanations

programming syntax elements related to function and method definitions

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

object or variable assignments

np_acts-logits-general · gemini-2.5-flash-lite

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

 tedy

-0.36

 lourd

-0.35

 hefty

-0.34

 parezca

-0.33

 tiek

-0.32

LLP

-0.32

lelő

-0.32

льники

-0.31

 privado

-0.31

 delight

-0.31

POSITIVE LOGITS

MigrationBuilder

0.66

 ſte

0.56

 tranſ

0.56

httphttps

0.52

IUrlHelper

0.51

fillType

0.50

تفصیلات

0.50

styleType

0.49

 ſche

0.48

Datuak

0.47

Activations Density 0.004%

programming syntax elements related to function and method definitions

object or variable assignments

No Comments

No Known Activations