INDEX

Explanations

programming-related terms, especially those associated with data handling and fetching

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

data, json, fetch

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

 nahilalakip

-0.60

GTCX

-0.57

+#+#

-0.54

ьаж

-0.53

 betweenstory

-0.52

bkz

-0.49

 Cæsar

-0.48

 onOptions

-0.48

 bezeichneter

-0.48

featureID

-0.48

POSITIVE LOGITS

kritik

0.34

fő

0.34

 adelantado

0.33

CTOR

0.33

 adelant

0.32

 arrives

0.32

 اعتبار

0.32

 Pader

0.32

fő

0.32

Malformed

0.32

Activations Density 0.009%

programming-related terms, especially those associated with data handling and fetching

data, json, fetch

No Comments

No Known Activations