INDEX

Explanations

occurrences of user-related terms and time units within 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 variés

-0.63

 engraçadas

-0.59

 segreto

-0.58

bootstrapcdn

-0.58

athione

-0.51

 commerciaux

-0.51

 segredo

-0.50

 réguli

-0.49

 exclusivas

-0.49

 actuelles

-0.49

POSITIVE LOGITS

 typelib

0.87

 تضيفلها

0.78

 autorytatywna

0.76

帖最后由

0.73

$_['

0.73



0.71

InputBorder

0.71

 CreateTagHelper

0.71

httphttps

0.70

 <=",

0.66

Activations Density 0.014%

occurrences of user-related terms and time units within programming contexts

No Comments

No Known Activations