INDEX

Explanations

programming constructs and structures related to method definitions and argument lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

WebElementEntity

-1.02

ьаж

-0.86

findpost

-0.83

 ligiloj

-0.82

 autorytatywna

-0.81

fjspx

-0.80

 snippetHide

-0.74

 BoxFit

-0.72

AndEndTag

-0.71

帖最后由

-0.71

POSITIVE LOGITS

JMenu

0.52

новниш

0.51

Unused

0.44

 forgotten

0.43

inguém

0.42

Assignable

0.42

 rolling

0.42

 неизвест

0.41

rimônio

0.41

rolling

0.41

Activations Density 0.342%

programming constructs and structures related to method definitions and argument lists

No Comments

No Known Activations