INDEX

Explanations

instances of the term "Ly" and variations indicating various states or levels in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

CommandText

-0.66

}\]

-0.62

 Lawton

-0.61

 kasarigan

-0.58

kháu

-0.57

SpringRunner

-0.57

ressum

-0.56

Vidite

-0.56

 Bioaccumulative

-0.55

ITHUB

-0.54

POSITIVE LOGITS

Ly

1.14

Ly

1.05

Ref

0.89

Datuak

0.82

ly

0.80

Ap

0.70

مصادر

0.70

Ap

0.69

DECREF

0.66

Collegamenti

0.62

Activations Density 0.116%

instances of the term "Ly" and variations indicating various states or levels in scientific contexts

No Comments

No Known Activations