INDEX

Explanations

code-related keywords and function definitions in programming documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

expandindo

-1.04

 betweenstory

-0.96

 Infórmanos

-0.94

帖最后由

-0.92

httphttps

-0.90

ValueStyle

-0.88

 jsPsych

-0.86

MLLoader

-0.85

GEBURTSDATUM

-0.84

.*")]

-0.82

POSITIVE LOGITS

 apparently

0.42

 reportedly

0.40

 automatically

0.38

 evidently

0.36

 report

0.35

 Kälte

0.35

 unsur

0.33

 still

0.32

 avan

0.31

 advanced

0.31

Activations Density 0.972%

code-related keywords and function definitions in programming documentation

No Comments

No Known Activations