INDEX

Explanations

specific terms related to computer hardware and internal components

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

Computer hardware/components

np_acts-logits-general · gemini-2.0-flash

internal pc components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

enumii

-0.57

enumi

-0.56

RenderAtEndOf

-0.54

 ***!

-0.54

 faſt

-0.53

exitRule

-0.51

 itſelf

-0.49

 Reſ

-0.49

 occaf

-0.49

 Monfieur

-0.48

POSITIVE LOGITS

 motherboard

0.46

setContentView

0.41

 chassis

0.40

Internal

0.40

SaveChangesAsync

0.38

 assembly

0.37

 Internal

0.37

Assembly

0.37

 componentes

0.37

INTERNAL

0.37

Activations Density 0.362%

specific terms related to computer hardware and internal components

Computer hardware/components

internal pc components

No Comments

No Known Activations