INDEX

Explanations

negative sentiments or criticisms relating to various contexts

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

Text after a hyphen

np_acts-logits-general · gemini-2.0-flash

compound word components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.96

BorderFactory

-0.53

UnknownFieldSet

-0.50

 Auvergne

-0.49

 Monfieur

-0.49

ConverterFactory

-0.48

closePath

-0.48

jnych

-0.47

 Myron

-0.47

 cigars

-0.47

POSITIVE LOGITS

 للمعارف

0.65

 viewDidLoad

0.61

 numberOfRows

0.58

帖最后由

0.57

thâu

0.57

ThroughAttribute

0.56

 мѣ

0.55

SourceChecksum

0.55

 الدولى

0.54

 podjela

0.53

Activations Density 0.352%

negative sentiments or criticisms relating to various contexts

Text after a hyphen

compound word components

No Comments

No Known Activations