INDEX

Explanations

technical terms and specifications relating to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.72

setVerticalGroup

-0.72



-0.63

 internetowa

-0.62

下载附件

-0.60

Chham

-0.59

̍t

-0.57

httphttps

-0.57

رشف

-0.55

metto

-0.55

POSITIVE LOGITS

 default

0.62

default

0.61

Default

0.60

默认

0.59

 defaults

0.59

 默认

0.58

SetDefault

0.56

ngOnInit

0.55

defaults

0.55

 Default

0.54

Activations Density 0.845%

technical terms and specifications relating to programming and data structures

No Comments

No Known Activations