INDEX

Explanations

references to database rows and columns 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 @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

aarrggbb

-0.83

 estekak

-0.68

={()=>

-0.66

mapStateToProps

-0.61

="#"><

-0.61

 }}"></

-0.61

HomeAsUp

-0.60

endpush

-0.59

ellants

-0.59

/******/

-0.58

POSITIVE LOGITS

rows

2.88

Rows

2.69

 rows

2.40

 Rows

2.13

ROWS

1.74

cols

1.23

 filas

1.16

 columns

1.05

filas

1.00

numRows

0.99

Activations Density 0.104%

references to database rows and columns in programming contexts

No Comments

No Known Activations