INDEX

Explanations

terms related to proper subsets and their properties

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

proper subset, properly

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.65

inSlope

-0.52

 transfieras

-0.51

oldest

-0.48

 ivelany

-0.46

UnknownFieldSet

-0.44

atoga

-0.43

jewish

-0.43

ostasis

-0.42

 CreateTagHelper

-0.41

POSITIVE LOGITS

 proper

0.78

 Proper

0.72

 PROPER

0.69

Proper

0.68

proper

0.62

 соб

0.57

 proprement

0.57

 propria

0.56

 propri

0.55

 properly

0.55

Activations Density 0.053%

terms related to proper subsets and their properties

proper subset, properly

No Comments

No Known Activations