INDEX

Explanations

terms related to auto-detection and mappings in a programming context

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

autodiscovery, automatic, detected

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

featureID

-0.55

 purpoſe

-0.54

setViewportView

-0.51

 jScrollPane

-0.47

 cauſe

-0.46

ronpa

-0.45

StoryboardSegue

-0.45

erçe

-0.45

IsMutable

-0.45

 Reſ

-0.44

POSITIVE LOGITS

 Automatic

0.53

rinfo

0.49

 automatic

0.48

 automatically

0.47

InjectAttribute

0.46

تقاوى

0.45

automatic

0.44

AUTO

0.42

autoconfigure

0.42

 自动

0.42

Activations Density 0.249%

terms related to auto-detection and mappings in a programming context

autodiscovery, automatic, detected

No Comments

No Known Activations