INDEX

Explanations

discussions surrounding professional training and organizational concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 tranſ

-0.66

 houſe

-0.65

 faſt

-0.63

 julk

-0.62

 viſ

-0.61

 cauſe

-0.58

 raiſ

-0.58

 myſelf

-0.57

 intitulée

-0.56

 ſeveral

-0.56

POSITIVE LOGITS

#+#

0.76

 PhpStorm

0.58

openzeppelin

0.57

CloseOperation

0.56

%@",

0.53

DrawerToggle

0.53

 protoimpl

0.53

 DialogResult

0.52

'):

0.52

},

0.51

Activations Density 0.238%

discussions surrounding professional training and organizational concerns

No Comments

No Known Activations