INDEX

Explanations

terms and concepts related to requirements, assumptions, and mechanisms in scientific or technical contexts

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

Followed by a number or Roman numeral

np_acts-logits-general · gemini-2.0-flash

numbers and labels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

httphttps

-0.81

帖最后由

-0.67

detectChanges

-0.65

']))

-0.60

}();

-0.59

}</

-0.56

 ""],

-0.56

Diwedd

-0.56

 gainera

-0.55

uxxxx

-0.54

POSITIVE LOGITS

 number

0.66

 Nummer

0.60

 nummer

0.58

ValueStyle

0.55

اریخ

0.55

number

0.55

0.54

UserScript

0.54

 numero

0.53

keye

0.53

Activations Density 0.833%

terms and concepts related to requirements, assumptions, and mechanisms in scientific or technical contexts

Followed by a number or Roman numeral

numbers and labels

No Comments

No Known Activations