INDEX

Explanations

references to structures related to defense and fortification

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

Uncommon or archaic words

np_acts-logits-general · gemini-2.0-flash

medical and scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 EconPapers

-0.61

WebElementEntity

-0.60

Hentet

-0.51

 dAtA

-0.50

UnknownFieldSet

-0.47

adaptiveStyles

-0.46

 general

-0.46

 really

-0.46

Everywhere

-0.44

￣)

-0.43

POSITIVE LOGITS

 ſever

0.84

<bos>

0.83

NameInMap

0.82

 Verſ

0.82

 disambiguazione

0.81

ſelf

0.81

 iſt

0.80

 verſ

0.76

 itſelf

0.75

 againſt

0.75

Activations Density 0.653%

references to structures related to defense and fortification

Uncommon or archaic words

medical and scientific contexts

No Comments

No Known Activations