INDEX

Explanations

terms related to multiple occurrences or references of symbols and instances in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

endphp

-0.72

 Parac

-0.67

 siguran

-0.63

 barbati

-0.63

 Geset

-0.60

 endblock

-0.58

 cedo

-0.57

 Fichier

-0.57

 opposes

-0.56

 joaat

-0.56

POSITIVE LOGITS

 correct

0.93

 instances

0.91

########.

0.82

instances

0.80

Instances

0.79

 Instances

0.71

ंदीखरीदारी

0.70

INSTANCE

0.69

 damn

0.65

getInstance

0.65

Activations Density 0.101%

terms related to multiple occurrences or references of symbols and instances in programming contexts

No Comments

No Known Activations