INDEX

Explanations

technical terms and constructs related to programming and software development

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

detector, sampler, extend, statistics, map

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

webElementXpaths

-0.80

URLException

-0.73

ⓧ

-0.69

ThroughAttribute

-0.67

styleType

-0.67

 utafitiHapana

-0.66

BeginContext

-0.66

WebElementEntity

-0.65

󠁴

-0.62

 ModelExpression

-0.61

POSITIVE LOGITS

FDRE

0.38

ๆ

0.37

 progress

0.37

 Winchester

0.36

ๆ

0.35

 system

0.35

Progress

0.34

Exped

0.34

 bisiklet

0.34

 control

0.34

Activations Density 0.042%

technical terms and constructs related to programming and software development

detector, sampler, extend, statistics, map

No Comments

No Known Activations