INDEX

Explanations

terms related to complex systems or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

脚注の使い方

-0.80

Попис

-0.66

migrationBuilder

-0.64

 sessionFactory

-0.63

HMIS

-0.62

Хьажоргаш

-0.61

 jsPsych

-0.60

pero

-0.59

afat

-0.58

structor

-0.57

POSITIVE LOGITS

GEBURTSDATUM

0.56

Rhestr

0.51

Parcelize

0.49

MethodType

0.49

WebElementEntity

0.48

TagMode

0.48

#+#

0.46

 proprement

0.45

RetentionPolicy

0.45

 propOrder

0.43

Activations Density 0.586%

terms related to complex systems or processes

No Comments

No Known Activations