INDEX

Explanations

lines of code or code fragments that include preprocessor directives and type declarations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 guerres

-0.66

цездатний

-0.66

 Winchester

-0.65

 Nacionales

-0.65

 danos

-0.65

 gratuits

-0.64

 sauvages

-0.63

 eletrônico

-0.62

ⓧ

-0.61

 voisins

-0.61

POSITIVE LOGITS

</thead>

0.64

 Besøkt

0.63

0.62

TagMode

0.61

tabular

0.56

archiviato

0.54

égard

0.54

AccessorTable

0.53

lut

0.53

endphp

0.52

Activations Density 0.063%

lines of code or code fragments that include preprocessor directives and type declarations

No Comments

No Known Activations